Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2625 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5604. Min Range: -9.5604
Max Act: 9.5604. Min Act: -0.1700
Data Index: 2673187 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5604. Min Range: -9.5604
Max Act: 9.4979. Min Act: -0.1700
Data Index: 4837771 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5604. Min Range: -9.5604
Max Act: 9.4354. Min Act: -0.1700
Data Index: 5342344 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5604. Min Range: -9.5604
Max Act: 9.4354. Min Act: -0.1700
Data Index: 549320 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5604. Min Range: -9.5604
Max Act: 9.3729. Min Act: -0.1700
Data Index: 1320001 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5604. Min Range: -9.5604
Max Act: 9.3729. Min Act: -0.1700
Data Index: 8349216 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5604. Min Range: -9.5604
Max Act: 9.3729. Min Act: -0.1700
Data Index: 8472591 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5604. Min Range: -9.5604
Max Act: 9.3104. Min Act: -0.1700
Data Index: 3160325 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5604. Min Range: -9.5604
Max Act: 9.2479. Min Act: -0.1700
Data Index: 5198893 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5604. Min Range: -9.5604
Max Act: 9.1854. Min Act: -0.1700
Data Index: 4603105 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5604. Min Range: -9.5604
Max Act: 9.1854. Min Act: -0.1700
Data Index: 2350782 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5604. Min Range: -9.5604
Max Act: 9.1854. Min Act: -0.1700
Data Index: 4601989 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5604. Min Range: -9.5604
Max Act: 9.1854. Min Act: -0.1700
Data Index: 7962807 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5604. Min Range: -9.5604
Max Act: 9.1854. Min Act: -0.1700
Data Index: 1081205 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5604. Min Range: -9.5604
Max Act: 9.1229. Min Act: -0.1700
Data Index: 480308 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5604. Min Range: -9.5604
Max Act: 9.1229. Min Act: -0.1700
Data Index: 6933336 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5604. Min Range: -9.5604
Max Act: 9.1229. Min Act: -0.1700
Data Index: 7305157 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5604. Min Range: -9.5604
Max Act: 9.1229. Min Act: -0.1700
Data Index: 2606464 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5604. Min Range: -9.5604
Max Act: 9.0604. Min Act: -0.1700
Data Index: 642204 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5604. Min Range: -9.5604
Max Act: 9.0604. Min Act: -0.1700
Data Index: 7615326 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19