Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4431 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5305. Min Range: -3.5305
Max Act: 3.5305. Min Act: -0.1700
Data Index: 6545415 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5305. Min Range: -3.5305
Max Act: 3.4835. Min Act: -0.1700
Data Index: 3406796 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5305. Min Range: -3.5305
Max Act: 3.3267. Min Act: -0.1700
Data Index: 167803 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5305. Min Range: -3.5305
Max Act: 3.3110. Min Act: -0.1700
Data Index: 3388976 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5305. Min Range: -3.5305
Max Act: 3.2953. Min Act: -0.1700
Data Index: 5907817 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5305. Min Range: -3.5305
Max Act: 3.2796. Min Act: -0.1700
Data Index: 3490084 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5305. Min Range: -3.5305
Max Act: 3.2796. Min Act: -0.1700
Data Index: 405834 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5305. Min Range: -3.5305
Max Act: 3.2482. Min Act: -0.1700
Data Index: 2663946 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5305. Min Range: -3.5305
Max Act: 3.2325. Min Act: -0.1700
Data Index: 5071249 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5305. Min Range: -3.5305
Max Act: 3.1853. Min Act: -0.1700
Data Index: 5694950 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5305. Min Range: -3.5305
Max Act: 3.1696. Min Act: -0.1700
Data Index: 6409814 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5305. Min Range: -3.5305
Max Act: 3.1696. Min Act: -0.1700
Data Index: 6616813 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5305. Min Range: -3.5305
Max Act: 3.1538. Min Act: -0.1700
Data Index: 8366305 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5305. Min Range: -3.5305
Max Act: 3.1853. Min Act: -0.1700
Data Index: 5262485 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5305. Min Range: -3.5305
Max Act: 3.1538. Min Act: -0.1700
Data Index: 1755002 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5305. Min Range: -3.5305
Max Act: 3.1381. Min Act: -0.1700
Data Index: 5156630 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5305. Min Range: -3.5305
Max Act: 3.1538. Min Act: -0.1700
Data Index: 106817 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5305. Min Range: -3.5305
Max Act: 3.1223. Min Act: -0.1700
Data Index: 6296583 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5305. Min Range: -3.5305
Max Act: 3.1381. Min Act: -0.1700
Data Index: 6641437 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5305. Min Range: -3.5305
Max Act: 3.1381. Min Act: -0.1700
Data Index: 6434196 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19