Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1507 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8933. Min Range: -1.8933
Max Act: 1.8933. Min Act: -0.1697
Data Index: 4085580 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8933. Min Range: -1.8933
Max Act: 1.8591. Min Act: -0.1700
Data Index: 3928793 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8933. Min Range: -1.8933
Max Act: 1.8676. Min Act: -0.1700
Data Index: 4801528 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8933. Min Range: -1.8933
Max Act: 1.8676. Min Act: -0.1700
Data Index: 5732189 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8933. Min Range: -1.8933
Max Act: 1.8505. Min Act: -0.1700
Data Index: 8015 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8933. Min Range: -1.8933
Max Act: 1.8676. Min Act: -0.1700
Data Index: 4605253 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8933. Min Range: -1.8933
Max Act: 1.8591. Min Act: -0.1695
Data Index: 7164289 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8933. Min Range: -1.8933
Max Act: 1.8591. Min Act: -0.1648
Data Index: 1373433 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8933. Min Range: -1.8933
Max Act: 1.8505. Min Act: -0.1700
Data Index: 4767631 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8933. Min Range: -1.8933
Max Act: 1.8248. Min Act: -0.1696
Data Index: 5251375 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8933. Min Range: -1.8933
Max Act: 1.8076. Min Act: -0.1700
Data Index: 6881864 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8933. Min Range: -1.8933
Max Act: 1.8334. Min Act: -0.1694
Data Index: 3501382 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8933. Min Range: -1.8933
Max Act: 1.8248. Min Act: -0.1256
Data Index: 936234 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8933. Min Range: -1.8933
Max Act: 1.8334. Min Act: -0.1700
Data Index: 3501381 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8933. Min Range: -1.8933
Max Act: 1.8248. Min Act: -0.1700
Data Index: 2643756 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8933. Min Range: -1.8933
Max Act: 1.8162. Min Act: -0.1683
Data Index: 8047040 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8933. Min Range: -1.8933
Max Act: 1.8076. Min Act: -0.1700
Data Index: 7702965 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8933. Min Range: -1.8933
Max Act: 1.8076. Min Act: -0.1700
Data Index: 2976218 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8933. Min Range: -1.8933
Max Act: 1.7990. Min Act: -0.1700
Data Index: 2758944 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8933. Min Range: -1.8933
Max Act: 1.7990. Min Act: -0.1700
Data Index: 7493544 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #19