Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2846 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1791. Min Range: -5.1791
Max Act: 5.1791. Min Act: -0.1700
Data Index: 6221418 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1791. Min Range: -5.1791
Max Act: 5.0853. Min Act: -0.1700
Data Index: 2426582 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1791. Min Range: -5.1791
Max Act: 5.0541. Min Act: -0.1700
Data Index: 4288766 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1791. Min Range: -5.1791
Max Act: 5.0228. Min Act: -0.1700
Data Index: 2426585 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1791. Min Range: -5.1791
Max Act: 4.9916. Min Act: -0.1700
Data Index: 6221414 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1791. Min Range: -5.1791
Max Act: 4.9603. Min Act: -0.1700
Data Index: 3230118 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1791. Min Range: -5.1791
Max Act: 4.9916. Min Act: -0.1700
Data Index: 7399463 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1791. Min Range: -5.1791
Max Act: 4.9916. Min Act: -0.1700
Data Index: 15725 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1791. Min Range: -5.1791
Max Act: 4.9603. Min Act: -0.1700
Data Index: 4819142 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1791. Min Range: -5.1791
Max Act: 4.9603. Min Act: -0.1700
Data Index: 2426583 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1791. Min Range: -5.1791
Max Act: 4.9603. Min Act: -0.1700
Data Index: 7059544 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1791. Min Range: -5.1791
Max Act: 4.9603. Min Act: -0.1700
Data Index: 994460 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1791. Min Range: -5.1791
Max Act: 4.9603. Min Act: -0.1700
Data Index: 5318169 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1791. Min Range: -5.1791
Max Act: 4.9291. Min Act: -0.1700
Data Index: 6911467 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1791. Min Range: -5.1791
Max Act: 4.9291. Min Act: -0.1700
Data Index: 2729817 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1791. Min Range: -5.1791
Max Act: 4.9291. Min Act: -0.1700
Data Index: 4777680 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1791. Min Range: -5.1791
Max Act: 4.9291. Min Act: -0.1699
Data Index: 3030288 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1791. Min Range: -5.1791
Max Act: 4.9291. Min Act: -0.1700
Data Index: 4464863 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1791. Min Range: -5.1791
Max Act: 4.9291. Min Act: -0.1700
Data Index: 2293207 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1791. Min Range: -5.1791
Max Act: 4.8978. Min Act: -0.1700
Data Index: 4239542 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19