Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3507 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3818. Min Range: -5.3818
Max Act: 5.3818. Min Act: -0.1700
Data Index: 4011870 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3818. Min Range: -5.3818
Max Act: 5.1630. Min Act: -0.1700
Data Index: 7186987 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3818. Min Range: -5.3818
Max Act: 5.1005. Min Act: -0.1700
Data Index: 6523755 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3818. Min Range: -5.3818
Max Act: 5.0693. Min Act: -0.1700
Data Index: 4619585 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3818. Min Range: -5.3818
Max Act: 5.0380. Min Act: -0.1700
Data Index: 4419978 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3818. Min Range: -5.3818
Max Act: 5.0380. Min Act: -0.1700
Data Index: 140141 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3818. Min Range: -5.3818
Max Act: 5.0693. Min Act: -0.1700
Data Index: 1363617 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3818. Min Range: -5.3818
Max Act: 4.9755. Min Act: -0.1700
Data Index: 5543728 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3818. Min Range: -5.3818
Max Act: 5.0068. Min Act: -0.1700
Data Index: 3401392 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3818. Min Range: -5.3818
Max Act: 5.0068. Min Act: -0.1700
Data Index: 132090 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3818. Min Range: -5.3818
Max Act: 5.0068. Min Act: -0.1700
Data Index: 1105001 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3818. Min Range: -5.3818
Max Act: 4.9755. Min Act: -0.1700
Data Index: 1264246 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3818. Min Range: -5.3818
Max Act: 4.9442. Min Act: -0.1700
Data Index: 1844315 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3818. Min Range: -5.3818
Max Act: 4.9442. Min Act: -0.1700
Data Index: 5518762 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3818. Min Range: -5.3818
Max Act: 4.9442. Min Act: -0.1700
Data Index: 7450096 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3818. Min Range: -5.3818
Max Act: 4.9442. Min Act: -0.1700
Data Index: 796824 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3818. Min Range: -5.3818
Max Act: 4.9442. Min Act: -0.1700
Data Index: 6148931 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3818. Min Range: -5.3818
Max Act: 4.8817. Min Act: -0.1700
Data Index: 325054 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3818. Min Range: -5.3818
Max Act: 4.9130. Min Act: -0.1700
Data Index: 4538030 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3818. Min Range: -5.3818
Max Act: 4.8817. Min Act: -0.1700
Data Index: 6883787 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19