Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3456 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.8939. Min Act: -0.1700
Data Index: 3560457 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.5814. Min Act: -0.1700
Data Index: 5287981 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.5189. Min Act: -0.1700
Data Index: 8653826 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.3626. Min Act: -0.1700
Data Index: 3064253 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.3314. Min Act: -0.1700
Data Index: 2100954 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.1751. Min Act: -0.1700
Data Index: 2364376 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.1751. Min Act: -0.1700
Data Index: 5282889 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.1439. Min Act: -0.1700
Data Index: 8751855 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8939. Min Range: -7.8939
Max Act: 7.0814. Min Act: -0.1700
Data Index: 1087643 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8939. Min Range: -7.8939
Max Act: 6.9564. Min Act: -0.1700
Data Index: 2899015 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8939. Min Range: -7.8939
Max Act: 6.9876. Min Act: -0.1700
Data Index: 5966904 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8939. Min Range: -7.8939
Max Act: 6.8939. Min Act: -0.1700
Data Index: 6313298 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8939. Min Range: -7.8939
Max Act: 6.8626. Min Act: -0.1700
Data Index: 2919306 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8939. Min Range: -7.8939
Max Act: 6.8626. Min Act: -0.1700
Data Index: 2039534 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8939. Min Range: -7.8939
Max Act: 6.8626. Min Act: -0.1700
Data Index: 2246032 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8939. Min Range: -7.8939
Max Act: 6.8626. Min Act: -0.1700
Data Index: 1115944 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8939. Min Range: -7.8939
Max Act: 6.8626. Min Act: -0.1700
Data Index: 5879632 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8939. Min Range: -7.8939
Max Act: 6.8626. Min Act: -0.1700
Data Index: 207148 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8939. Min Range: -7.8939
Max Act: 6.8314. Min Act: -0.1700
Data Index: 7170440 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8939. Min Range: -7.8939
Max Act: 6.8314. Min Act: -0.1700
Data Index: 1115941 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19