Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2428 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2786. Min Range: -9.2786
Max Act: 9.2786. Min Act: -0.1700
Data Index: 5547300 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2786. Min Range: -9.2786
Max Act: 8.6536. Min Act: -0.1700
Data Index: 8004738 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2786. Min Range: -9.2786
Max Act: 8.4661. Min Act: -0.1700
Data Index: 8446516 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2786. Min Range: -9.2786
Max Act: 8.4036. Min Act: -0.1700
Data Index: 7025785 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2786. Min Range: -9.2786
Max Act: 8.3411. Min Act: -0.1700
Data Index: 453764 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2786. Min Range: -9.2786
Max Act: 8.2786. Min Act: -0.1700
Data Index: 147391 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2786. Min Range: -9.2786
Max Act: 8.1536. Min Act: -0.1700
Data Index: 2038802 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2786. Min Range: -9.2786
Max Act: 8.1223. Min Act: -0.1700
Data Index: 5954422 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2786. Min Range: -9.2786
Max Act: 8.0911. Min Act: -0.1700
Data Index: 6950350 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2786. Min Range: -9.2786
Max Act: 7.9661. Min Act: -0.1700
Data Index: 2096802 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2786. Min Range: -9.2786
Max Act: 7.9348. Min Act: -0.1700
Data Index: 2883056 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2786. Min Range: -9.2786
Max Act: 7.8723. Min Act: -0.1700
Data Index: 4224055 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2786. Min Range: -9.2786
Max Act: 7.9036. Min Act: -0.1700
Data Index: 7654361 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2786. Min Range: -9.2786
Max Act: 7.9036. Min Act: -0.1700
Data Index: 3291520 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2786. Min Range: -9.2786
Max Act: 7.8723. Min Act: -0.1700
Data Index: 919680 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2786. Min Range: -9.2786
Max Act: 7.9036. Min Act: -0.1700
Data Index: 4849448 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2786. Min Range: -9.2786
Max Act: 7.8411. Min Act: -0.1700
Data Index: 973648 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2786. Min Range: -9.2786
Max Act: 7.8411. Min Act: -0.1700
Data Index: 7104211 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2786. Min Range: -9.2786
Max Act: 7.7473. Min Act: -0.1700
Data Index: 1231282 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2786. Min Range: -9.2786
Max Act: 7.7161. Min Act: -0.1700
Data Index: 4761671 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19