Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1006 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7471. Min Range: -4.7471
Max Act: 4.7471. Min Act: -0.1700
Data Index: 7570550 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7471. Min Range: -4.7471
Max Act: 4.5908. Min Act: -0.1700
Data Index: 5724224 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7471. Min Range: -4.7471
Max Act: 4.5596. Min Act: -0.1700
Data Index: 1396038 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7471. Min Range: -4.7471
Max Act: 4.5283. Min Act: -0.1700
Data Index: 1008180 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7471. Min Range: -4.7471
Max Act: 4.4971. Min Act: -0.1700
Data Index: 2017790 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7471. Min Range: -4.7471
Max Act: 4.4658. Min Act: -0.1700
Data Index: 4495010 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7471. Min Range: -4.7471
Max Act: 4.4658. Min Act: -0.1700
Data Index: 3573639 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7471. Min Range: -4.7471
Max Act: 4.4658. Min Act: -0.1700
Data Index: 6310379 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7471. Min Range: -4.7471
Max Act: 4.4658. Min Act: -0.1700
Data Index: 4159431 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7471. Min Range: -4.7471
Max Act: 4.4345. Min Act: -0.1700
Data Index: 3649327 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7471. Min Range: -4.7471
Max Act: 4.4033. Min Act: -0.1700
Data Index: 4997166 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7471. Min Range: -4.7471
Max Act: 4.4033. Min Act: -0.1700
Data Index: 4402134 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7471. Min Range: -4.7471
Max Act: 4.4345. Min Act: -0.1700
Data Index: 5297831 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7471. Min Range: -4.7471
Max Act: 4.4345. Min Act: -0.1700
Data Index: 1323904 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7471. Min Range: -4.7471
Max Act: 4.4345. Min Act: -0.1700
Data Index: 2840173 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7471. Min Range: -4.7471
Max Act: 4.4345. Min Act: -0.1700
Data Index: 735965 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7471. Min Range: -4.7471
Max Act: 4.4033. Min Act: -0.1700
Data Index: 1390396 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7471. Min Range: -4.7471
Max Act: 4.4033. Min Act: -0.1700
Data Index: 547689 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7471. Min Range: -4.7471
Max Act: 4.4033. Min Act: -0.1700
Data Index: 20979 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7471. Min Range: -4.7471
Max Act: 4.4033. Min Act: -0.1700
Data Index: 984493 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19