Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3208 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6410. Min Range: -7.6410
Max Act: 7.6410. Min Act: -0.1700
Data Index: 4883481 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6410. Min Range: -7.6410
Max Act: 7.2660. Min Act: -0.1700
Data Index: 284242 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6410. Min Range: -7.6410
Max Act: 7.2660. Min Act: -0.1700
Data Index: 3272246 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6410. Min Range: -7.6410
Max Act: 7.2347. Min Act: -0.1700
Data Index: 6874599 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6410. Min Range: -7.6410
Max Act: 7.2035. Min Act: -0.1700
Data Index: 8067527 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6410. Min Range: -7.6410
Max Act: 7.2035. Min Act: -0.1700
Data Index: 2786605 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6410. Min Range: -7.6410
Max Act: 7.1722. Min Act: -0.1700
Data Index: 2146962 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6410. Min Range: -7.6410
Max Act: 7.1410. Min Act: -0.1700
Data Index: 7463465 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6410. Min Range: -7.6410
Max Act: 7.1722. Min Act: -0.1700
Data Index: 2528706 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6410. Min Range: -7.6410
Max Act: 7.1097. Min Act: -0.1700
Data Index: 31322 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6410. Min Range: -7.6410
Max Act: 7.0785. Min Act: -0.1700
Data Index: 5366490 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6410. Min Range: -7.6410
Max Act: 7.1097. Min Act: -0.1700
Data Index: 6273941 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6410. Min Range: -7.6410
Max Act: 7.0785. Min Act: -0.1700
Data Index: 5249320 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6410. Min Range: -7.6410
Max Act: 7.0160. Min Act: -0.1700
Data Index: 5304557 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6410. Min Range: -7.6410
Max Act: 7.0472. Min Act: -0.1700
Data Index: 4843662 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6410. Min Range: -7.6410
Max Act: 7.0160. Min Act: -0.1700
Data Index: 4625711 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6410. Min Range: -7.6410
Max Act: 7.0160. Min Act: -0.1700
Data Index: 535707 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6410. Min Range: -7.6410
Max Act: 6.9847. Min Act: -0.1700
Data Index: 3000993 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6410. Min Range: -7.6410
Max Act: 6.9847. Min Act: -0.1700
Data Index: 4241720 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6410. Min Range: -7.6410
Max Act: 6.9847. Min Act: -0.1700
Data Index: 3690780 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19