Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2955 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0552. Min Range: -11.0552
Max Act: 11.0552. Min Act: -0.1700
Data Index: 7703135 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0552. Min Range: -11.0552
Max Act: 11.0552. Min Act: -0.1700
Data Index: 479223 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0552. Min Range: -11.0552
Max Act: 11.0552. Min Act: -0.1700
Data Index: 4077170 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0552. Min Range: -11.0552
Max Act: 10.9927. Min Act: -0.1700
Data Index: 2558857 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0552. Min Range: -11.0552
Max Act: 10.9302. Min Act: -0.1700
Data Index: 1199530 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0552. Min Range: -11.0552
Max Act: 10.8677. Min Act: -0.1700
Data Index: 7761606 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0552. Min Range: -11.0552
Max Act: 10.7427. Min Act: -0.1700
Data Index: 4325507 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0552. Min Range: -11.0552
Max Act: 10.6177. Min Act: -0.1700
Data Index: 768128 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0552. Min Range: -11.0552
Max Act: 10.6177. Min Act: -0.1700
Data Index: 8047578 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0552. Min Range: -11.0552
Max Act: 10.6177. Min Act: -0.1700
Data Index: 4835098 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0552. Min Range: -11.0552
Max Act: 10.5552. Min Act: -0.1700
Data Index: 2529460 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0552. Min Range: -11.0552
Max Act: 10.4927. Min Act: -0.1700
Data Index: 2887863 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0552. Min Range: -11.0552
Max Act: 10.4927. Min Act: -0.1700
Data Index: 2066618 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0552. Min Range: -11.0552
Max Act: 10.4927. Min Act: -0.1700
Data Index: 5149648 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0552. Min Range: -11.0552
Max Act: 10.4302. Min Act: -0.1700
Data Index: 4095768 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0552. Min Range: -11.0552
Max Act: 10.3677. Min Act: -0.1700
Data Index: 8054417 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0552. Min Range: -11.0552
Max Act: 10.4302. Min Act: -0.1700
Data Index: 8032065 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0552. Min Range: -11.0552
Max Act: 10.3677. Min Act: -0.1700
Data Index: 5710103 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0552. Min Range: -11.0552
Max Act: 10.3052. Min Act: -0.1700
Data Index: 2675490 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0552. Min Range: -11.0552
Max Act: 10.3677. Min Act: -0.1700
Data Index: 5791719 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19