Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3106 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5818. Min Range: -7.5818
Max Act: 7.5818. Min Act: -0.1700
Data Index: 447624 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5818. Min Range: -7.5818
Max Act: 7.5193. Min Act: -0.1700
Data Index: 3541591 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5818. Min Range: -7.5818
Max Act: 7.4255. Min Act: -0.1700
Data Index: 386894 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5818. Min Range: -7.5818
Max Act: 7.3318. Min Act: -0.1700
Data Index: 5652187 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5818. Min Range: -7.5818
Max Act: 7.3005. Min Act: -0.1700
Data Index: 1273800 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5818. Min Range: -7.5818
Max Act: 7.3005. Min Act: -0.1700
Data Index: 4196308 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5818. Min Range: -7.5818
Max Act: 7.2380. Min Act: -0.1700
Data Index: 5878395 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5818. Min Range: -7.5818
Max Act: 7.2380. Min Act: -0.1700
Data Index: 8752933 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5818. Min Range: -7.5818
Max Act: 7.1443. Min Act: -0.1700
Data Index: 5375685 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5818. Min Range: -7.5818
Max Act: 7.1443. Min Act: -0.1700
Data Index: 1149972 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5818. Min Range: -7.5818
Max Act: 7.1130. Min Act: -0.1700
Data Index: 7927455 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5818. Min Range: -7.5818
Max Act: 7.0818. Min Act: -0.1700
Data Index: 4528798 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5818. Min Range: -7.5818
Max Act: 6.9880. Min Act: -0.1700
Data Index: 996696 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5818. Min Range: -7.5818
Max Act: 6.9880. Min Act: -0.1700
Data Index: 3408331 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5818. Min Range: -7.5818
Max Act: 6.9568. Min Act: -0.1700
Data Index: 2006560 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5818. Min Range: -7.5818
Max Act: 6.9568. Min Act: -0.1700
Data Index: 8320979 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5818. Min Range: -7.5818
Max Act: 6.9568. Min Act: -0.1700
Data Index: 7147684 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5818. Min Range: -7.5818
Max Act: 6.9568. Min Act: -0.1700
Data Index: 8199913 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5818. Min Range: -7.5818
Max Act: 6.8943. Min Act: -0.1700
Data Index: 3999569 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5818. Min Range: -7.5818
Max Act: 6.9255. Min Act: -0.1700
Data Index: 6468311 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19