Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6353 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6505. Min Range: -8.6505
Max Act: 8.5880. Min Act: -0.1700
Data Index: 251644 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6505. Min Range: -8.6505
Max Act: 8.6505. Min Act: -0.1700
Data Index: 2587201 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6505. Min Range: -8.6505
Max Act: 8.4630. Min Act: -0.1700
Data Index: 7362259 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6505. Min Range: -8.6505
Max Act: 8.4630. Min Act: -0.1700
Data Index: 5762898 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6505. Min Range: -8.6505
Max Act: 8.4005. Min Act: -0.1700
Data Index: 5329051 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6505. Min Range: -8.6505
Max Act: 8.3380. Min Act: -0.1700
Data Index: 1411309 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6505. Min Range: -8.6505
Max Act: 8.3380. Min Act: -0.1700
Data Index: 5867978 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6505. Min Range: -8.6505
Max Act: 8.2755. Min Act: -0.1700
Data Index: 6555500 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6505. Min Range: -8.6505
Max Act: 8.2755. Min Act: -0.1700
Data Index: 5626778 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6505. Min Range: -8.6505
Max Act: 8.2130. Min Act: -0.1700
Data Index: 3082494 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6505. Min Range: -8.6505
Max Act: 8.1505. Min Act: -0.1700
Data Index: 2483892 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6505. Min Range: -8.6505
Max Act: 8.1505. Min Act: -0.1700
Data Index: 4058688 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6505. Min Range: -8.6505
Max Act: 8.2130. Min Act: -0.1700
Data Index: 7159121 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6505. Min Range: -8.6505
Max Act: 8.1505. Min Act: -0.1700
Data Index: 2069814 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6505. Min Range: -8.6505
Max Act: 8.1505. Min Act: -0.1700
Data Index: 3301744 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6505. Min Range: -8.6505
Max Act: 8.0880. Min Act: -0.1700
Data Index: 53350 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6505. Min Range: -8.6505
Max Act: 8.0880. Min Act: -0.1700
Data Index: 1492680 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6505. Min Range: -8.6505
Max Act: 8.0880. Min Act: -0.1700
Data Index: 938976 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6505. Min Range: -8.6505
Max Act: 8.0880. Min Act: -0.1700
Data Index: 2662495 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6505. Min Range: -8.6505
Max Act: 8.0880. Min Act: -0.1700
Data Index: 4366826 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19