Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5800 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5004. Min Range: -6.5004
Max Act: 6.5004. Min Act: -0.1700
Data Index: 4926808 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5004. Min Range: -6.5004
Max Act: 6.4692. Min Act: -0.1700
Data Index: 4103497 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5004. Min Range: -6.5004
Max Act: 6.3442. Min Act: -0.1700
Data Index: 3591677 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5004. Min Range: -6.5004
Max Act: 6.3442. Min Act: -0.1699
Data Index: 5459776 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5004. Min Range: -6.5004
Max Act: 6.3442. Min Act: -0.1700
Data Index: 2656242 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5004. Min Range: -6.5004
Max Act: 6.3442. Min Act: -0.1700
Data Index: 7087541 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5004. Min Range: -6.5004
Max Act: 6.3129. Min Act: -0.1700
Data Index: 4439149 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5004. Min Range: -6.5004
Max Act: 6.3129. Min Act: -0.1700
Data Index: 1436272 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5004. Min Range: -6.5004
Max Act: 6.3129. Min Act: -0.1694
Data Index: 161240 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5004. Min Range: -6.5004
Max Act: 6.3129. Min Act: -0.1700
Data Index: 8066675 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5004. Min Range: -6.5004
Max Act: 6.3129. Min Act: -0.1700
Data Index: 6303979 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5004. Min Range: -6.5004
Max Act: 6.3129. Min Act: -0.1700
Data Index: 40285 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5004. Min Range: -6.5004
Max Act: 6.2817. Min Act: -0.1700
Data Index: 7398761 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5004. Min Range: -6.5004
Max Act: 6.2817. Min Act: -0.1700
Data Index: 5153757 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5004. Min Range: -6.5004
Max Act: 6.2817. Min Act: -0.1700
Data Index: 1810120 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5004. Min Range: -6.5004
Max Act: 6.2504. Min Act: -0.1700
Data Index: 1190622 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5004. Min Range: -6.5004
Max Act: 6.2504. Min Act: -0.1700
Data Index: 5356154 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5004. Min Range: -6.5004
Max Act: 6.2504. Min Act: -0.1700
Data Index: 2664891 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5004. Min Range: -6.5004
Max Act: 6.2504. Min Act: -0.1700
Data Index: 5595421 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5004. Min Range: -6.5004
Max Act: 6.2504. Min Act: -0.1700
Data Index: 5745435 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19