Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3538 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.6381. Min Act: -0.1700
Data Index: 3533603 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.6537. Min Act: -0.1700
Data Index: 64329 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.5442. Min Act: -0.1700
Data Index: 5552582 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.5285. Min Act: -0.1700
Data Index: 6392479 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.5129. Min Act: -0.1700
Data Index: 1584323 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.3091. Min Act: -0.1700
Data Index: 2670016 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.2777. Min Act: -0.1700
Data Index: 8291955 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.2777. Min Act: -0.1700
Data Index: 4362553 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.2620. Min Act: -0.1700
Data Index: 541464 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.2777. Min Act: -0.1700
Data Index: 669379 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.2462. Min Act: -0.1700
Data Index: 6932681 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.2462. Min Act: -0.1700
Data Index: 7496536 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.2305. Min Act: -0.1700
Data Index: 7373533 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.2148. Min Act: -0.1700
Data Index: 5270194 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.1991. Min Act: -0.1700
Data Index: 6193383 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.1991. Min Act: -0.1700
Data Index: 1545358 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.1991. Min Act: -0.1700
Data Index: 851337 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.1834. Min Act: -0.1700
Data Index: 3995877 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.1834. Min Act: -0.1700
Data Index: 5231892 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.1834. Min Act: -0.1700
Data Index: 2304905 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19