Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3502 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2244. Min Range: -6.2244
Max Act: 6.2244. Min Act: -0.1700
Data Index: 6506032 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2244. Min Range: -6.2244
Max Act: 6.1619. Min Act: -0.1700
Data Index: 283511 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2244. Min Range: -6.2244
Max Act: 6.1307. Min Act: -0.1700
Data Index: 3851322 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2244. Min Range: -6.2244
Max Act: 6.1307. Min Act: -0.1700
Data Index: 6344314 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2244. Min Range: -6.2244
Max Act: 6.0057. Min Act: -0.1700
Data Index: 2511699 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2244. Min Range: -6.2244
Max Act: 5.9744. Min Act: -0.1700
Data Index: 8502839 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2244. Min Range: -6.2244
Max Act: 6.0057. Min Act: -0.1700
Data Index: 755172 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2244. Min Range: -6.2244
Max Act: 6.0057. Min Act: -0.1700
Data Index: 2149796 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2244. Min Range: -6.2244
Max Act: 6.0057. Min Act: -0.1700
Data Index: 2720489 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2244. Min Range: -6.2244
Max Act: 6.0057. Min Act: -0.1700
Data Index: 3823968 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2244. Min Range: -6.2244
Max Act: 5.9432. Min Act: -0.1700
Data Index: 5017990 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2244. Min Range: -6.2244
Max Act: 5.9119. Min Act: -0.1700
Data Index: 8017182 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2244. Min Range: -6.2244
Max Act: 5.9119. Min Act: -0.1700
Data Index: 6018209 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2244. Min Range: -6.2244
Max Act: 5.9119. Min Act: -0.1700
Data Index: 657194 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2244. Min Range: -6.2244
Max Act: 5.8494. Min Act: -0.1700
Data Index: 4125504 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2244. Min Range: -6.2244
Max Act: 5.8807. Min Act: -0.1700
Data Index: 1090783 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2244. Min Range: -6.2244
Max Act: 5.8807. Min Act: -0.1700
Data Index: 7438452 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2244. Min Range: -6.2244
Max Act: 5.8494. Min Act: -0.1700
Data Index: 7785811 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2244. Min Range: -6.2244
Max Act: 5.8494. Min Act: -0.1700
Data Index: 657190 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2244. Min Range: -6.2244
Max Act: 5.7869. Min Act: -0.1700
Data Index: 6984476 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19