Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4147 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5692. Min Range: -10.5692
Max Act: 10.5692. Min Act: -0.1700
Data Index: 3791226 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5692. Min Range: -10.5692
Max Act: 10.3817. Min Act: -0.1700
Data Index: 1342833 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5692. Min Range: -10.5692
Max Act: 10.1942. Min Act: -0.1700
Data Index: 4254840 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5692. Min Range: -10.5692
Max Act: 9.9442. Min Act: -0.1700
Data Index: 8437261 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5692. Min Range: -10.5692
Max Act: 9.8192. Min Act: -0.1700
Data Index: 817778 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5692. Min Range: -10.5692
Max Act: 9.6942. Min Act: -0.1700
Data Index: 6250373 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5692. Min Range: -10.5692
Max Act: 9.6317. Min Act: -0.1700
Data Index: 8432311 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5692. Min Range: -10.5692
Max Act: 9.6317. Min Act: -0.1700
Data Index: 4456579 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5692. Min Range: -10.5692
Max Act: 9.5692. Min Act: -0.1700
Data Index: 5628922 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5692. Min Range: -10.5692
Max Act: 9.5692. Min Act: -0.1700
Data Index: 6727182 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5692. Min Range: -10.5692
Max Act: 9.4442. Min Act: -0.1700
Data Index: 3978690 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5692. Min Range: -10.5692
Max Act: 9.3192. Min Act: -0.1700
Data Index: 7713163 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5692. Min Range: -10.5692
Max Act: 9.2567. Min Act: -0.1700
Data Index: 2124886 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5692. Min Range: -10.5692
Max Act: 9.1942. Min Act: -0.1700
Data Index: 4521090 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5692. Min Range: -10.5692
Max Act: 9.2567. Min Act: -0.1700
Data Index: 8316567 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5692. Min Range: -10.5692
Max Act: 9.2567. Min Act: -0.1700
Data Index: 3821099 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5692. Min Range: -10.5692
Max Act: 9.1942. Min Act: -0.1700
Data Index: 3082906 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5692. Min Range: -10.5692
Max Act: 9.1942. Min Act: -0.1700
Data Index: 7248957 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5692. Min Range: -10.5692
Max Act: 9.1942. Min Act: -0.1700
Data Index: 3375921 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5692. Min Range: -10.5692
Max Act: 9.2567. Min Act: -0.1700
Data Index: 4933328 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19