Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5658 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8396. Min Range: -6.8396
Max Act: 6.8396. Min Act: -0.1700
Data Index: 8096506 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8396. Min Range: -6.8396
Max Act: 6.8396. Min Act: -0.1700
Data Index: 5515283 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8396. Min Range: -6.8396
Max Act: 6.6521. Min Act: -0.1700
Data Index: 8146573 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8396. Min Range: -6.8396
Max Act: 6.6521. Min Act: -0.1700
Data Index: 3069575 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8396. Min Range: -6.8396
Max Act: 6.5896. Min Act: -0.1700
Data Index: 6007417 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8396. Min Range: -6.8396
Max Act: 6.4958. Min Act: -0.1700
Data Index: 2077177 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8396. Min Range: -6.8396
Max Act: 6.4333. Min Act: -0.1700
Data Index: 5292804 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8396. Min Range: -6.8396
Max Act: 6.4021. Min Act: -0.1700
Data Index: 7521340 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8396. Min Range: -6.8396
Max Act: 6.4021. Min Act: -0.1700
Data Index: 7771026 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8396. Min Range: -6.8396
Max Act: 6.3708. Min Act: -0.1700
Data Index: 3399687 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8396. Min Range: -6.8396
Max Act: 6.4021. Min Act: -0.1700
Data Index: 438136 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8396. Min Range: -6.8396
Max Act: 6.3708. Min Act: -0.1700
Data Index: 461823 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8396. Min Range: -6.8396
Max Act: 6.3708. Min Act: -0.1700
Data Index: 5722505 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8396. Min Range: -6.8396
Max Act: 6.3708. Min Act: -0.1700
Data Index: 2545315 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8396. Min Range: -6.8396
Max Act: 6.3708. Min Act: -0.1700
Data Index: 388615 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8396. Min Range: -6.8396
Max Act: 6.4021. Min Act: -0.1700
Data Index: 5413134 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8396. Min Range: -6.8396
Max Act: 6.3396. Min Act: -0.1700
Data Index: 3785715 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8396. Min Range: -6.8396
Max Act: 6.3396. Min Act: -0.1700
Data Index: 1719068 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8396. Min Range: -6.8396
Max Act: 6.3396. Min Act: -0.1700
Data Index: 3236215 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8396. Min Range: -6.8396
Max Act: 6.3083. Min Act: -0.1700
Data Index: 6078177 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19