Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3584 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8854. Min Range: -7.8854
Max Act: 7.8854. Min Act: -0.1700
Data Index: 3923844 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8854. Min Range: -7.8854
Max Act: 7.6354. Min Act: -0.1700
Data Index: 2364524 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8854. Min Range: -7.8854
Max Act: 7.6041. Min Act: -0.1700
Data Index: 6949679 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8854. Min Range: -7.8854
Max Act: 7.5729. Min Act: -0.1700
Data Index: 7448048 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8854. Min Range: -7.8854
Max Act: 7.5416. Min Act: -0.1700
Data Index: 5216480 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8854. Min Range: -7.8854
Max Act: 7.3541. Min Act: -0.1700
Data Index: 6320749 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8854. Min Range: -7.8854
Max Act: 7.2916. Min Act: -0.1700
Data Index: 8059134 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8854. Min Range: -7.8854
Max Act: 7.2916. Min Act: -0.1700
Data Index: 6398597 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8854. Min Range: -7.8854
Max Act: 7.2291. Min Act: -0.1700
Data Index: 4547553 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8854. Min Range: -7.8854
Max Act: 7.2291. Min Act: -0.1700
Data Index: 3793589 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8854. Min Range: -7.8854
Max Act: 7.2604. Min Act: -0.1700
Data Index: 7035874 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8854. Min Range: -7.8854
Max Act: 7.1979. Min Act: -0.1700
Data Index: 4035894 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8854. Min Range: -7.8854
Max Act: 7.2291. Min Act: -0.1700
Data Index: 7087022 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8854. Min Range: -7.8854
Max Act: 7.1979. Min Act: -0.1700
Data Index: 2248535 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8854. Min Range: -7.8854
Max Act: 7.1979. Min Act: -0.1700
Data Index: 8368543 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8854. Min Range: -7.8854
Max Act: 7.1666. Min Act: -0.1700
Data Index: 3384877 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8854. Min Range: -7.8854
Max Act: 7.1666. Min Act: -0.1700
Data Index: 982649 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8854. Min Range: -7.8854
Max Act: 7.1666. Min Act: -0.1700
Data Index: 6175599 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8854. Min Range: -7.8854
Max Act: 7.1354. Min Act: -0.1700
Data Index: 3256704 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8854. Min Range: -7.8854
Max Act: 7.1354. Min Act: -0.1700
Data Index: 5535449 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19