Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 850 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7473. Min Range: -5.7473
Max Act: 5.7473. Min Act: -0.1700
Data Index: 5777925 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7473. Min Range: -5.7473
Max Act: 5.7161. Min Act: -0.1700
Data Index: 5240041 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7473. Min Range: -5.7473
Max Act: 5.6536. Min Act: -0.1700
Data Index: 693224 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7473. Min Range: -5.7473
Max Act: 5.5911. Min Act: -0.1700
Data Index: 6310414 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7473. Min Range: -5.7473
Max Act: 5.5598. Min Act: -0.1700
Data Index: 4136784 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7473. Min Range: -5.7473
Max Act: 5.5598. Min Act: -0.1700
Data Index: 3295323 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7473. Min Range: -5.7473
Max Act: 5.5286. Min Act: -0.1700
Data Index: 2546713 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7473. Min Range: -5.7473
Max Act: 5.5286. Min Act: -0.1700
Data Index: 6967245 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7473. Min Range: -5.7473
Max Act: 5.4973. Min Act: -0.1700
Data Index: 7772507 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7473. Min Range: -5.7473
Max Act: 5.4973. Min Act: -0.1700
Data Index: 881181 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7473. Min Range: -5.7473
Max Act: 5.4973. Min Act: -0.1700
Data Index: 4059177 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7473. Min Range: -5.7473
Max Act: 5.4973. Min Act: -0.1700
Data Index: 3033062 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7473. Min Range: -5.7473
Max Act: 5.4973. Min Act: -0.1700
Data Index: 2555294 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7473. Min Range: -5.7473
Max Act: 5.4973. Min Act: -0.1700
Data Index: 2055418 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7473. Min Range: -5.7473
Max Act: 5.4973. Min Act: -0.1700
Data Index: 4214003 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7473. Min Range: -5.7473
Max Act: 5.4661. Min Act: -0.1700
Data Index: 5573348 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7473. Min Range: -5.7473
Max Act: 5.4661. Min Act: -0.1700
Data Index: 8509604 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7473. Min Range: -5.7473
Max Act: 5.4661. Min Act: -0.1700
Data Index: 6163142 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7473. Min Range: -5.7473
Max Act: 5.4661. Min Act: -0.1700
Data Index: 293731 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7473. Min Range: -5.7473
Max Act: 5.4348. Min Act: -0.1700
Data Index: 6170186 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19