Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3050 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7074. Min Range: -7.7074
Max Act: 7.7074. Min Act: -0.1700
Data Index: 898454 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7074. Min Range: -7.7074
Max Act: 7.6449. Min Act: -0.1700
Data Index: 4607750 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7074. Min Range: -7.7074
Max Act: 7.4574. Min Act: -0.1700
Data Index: 501940 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7074. Min Range: -7.7074
Max Act: 7.3949. Min Act: -0.1700
Data Index: 102778 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7074. Min Range: -7.7074
Max Act: 7.3636. Min Act: -0.1700
Data Index: 1314271 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7074. Min Range: -7.7074
Max Act: 7.3636. Min Act: -0.1700
Data Index: 987408 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7074. Min Range: -7.7074
Max Act: 7.3324. Min Act: -0.1700
Data Index: 7912278 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7074. Min Range: -7.7074
Max Act: 7.3324. Min Act: -0.1700
Data Index: 3949021 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7074. Min Range: -7.7074
Max Act: 7.2386. Min Act: -0.1700
Data Index: 6590413 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7074. Min Range: -7.7074
Max Act: 7.2699. Min Act: -0.1700
Data Index: 4899390 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7074. Min Range: -7.7074
Max Act: 7.2386. Min Act: -0.1700
Data Index: 6803751 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7074. Min Range: -7.7074
Max Act: 7.2074. Min Act: -0.1700
Data Index: 4258093 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7074. Min Range: -7.7074
Max Act: 7.1761. Min Act: -0.1700
Data Index: 1645617 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7074. Min Range: -7.7074
Max Act: 7.1761. Min Act: -0.1700
Data Index: 7937634 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7074. Min Range: -7.7074
Max Act: 7.1449. Min Act: -0.1700
Data Index: 224850 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7074. Min Range: -7.7074
Max Act: 7.1449. Min Act: -0.1700
Data Index: 5880304 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7074. Min Range: -7.7074
Max Act: 7.1136. Min Act: -0.1700
Data Index: 560410 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7074. Min Range: -7.7074
Max Act: 7.1449. Min Act: -0.1700
Data Index: 8206127 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7074. Min Range: -7.7074
Max Act: 7.1449. Min Act: -0.1700
Data Index: 3911922 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7074. Min Range: -7.7074
Max Act: 7.0511. Min Act: -0.1700
Data Index: 1477850 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19