Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1970 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9352. Min Range: -5.9352
Max Act: 5.9352. Min Act: -0.1700
Data Index: 7794771 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9352. Min Range: -5.9352
Max Act: 5.9039. Min Act: -0.1700
Data Index: 3120291 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9352. Min Range: -5.9352
Max Act: 5.9352. Min Act: -0.1700
Data Index: 2474778 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9352. Min Range: -5.9352
Max Act: 5.9039. Min Act: -0.1700
Data Index: 5042331 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9352. Min Range: -5.9352
Max Act: 5.9039. Min Act: -0.1700
Data Index: 3426350 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9352. Min Range: -5.9352
Max Act: 5.8414. Min Act: -0.1700
Data Index: 5727417 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9352. Min Range: -5.9352
Max Act: 5.7477. Min Act: -0.1700
Data Index: 174366 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9352. Min Range: -5.9352
Max Act: 5.6852. Min Act: -0.1700
Data Index: 6585921 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9352. Min Range: -5.9352
Max Act: 5.6852. Min Act: -0.1700
Data Index: 2901872 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9352. Min Range: -5.9352
Max Act: 5.5602. Min Act: -0.1700
Data Index: 2096017 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9352. Min Range: -5.9352
Max Act: 5.4977. Min Act: -0.1700
Data Index: 7984768 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9352. Min Range: -5.9352
Max Act: 5.4977. Min Act: -0.1700
Data Index: 8620377 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9352. Min Range: -5.9352
Max Act: 5.4664. Min Act: -0.1700
Data Index: 4591578 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9352. Min Range: -5.9352
Max Act: 5.4664. Min Act: -0.1700
Data Index: 4609794 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9352. Min Range: -5.9352
Max Act: 5.4352. Min Act: -0.1700
Data Index: 38636 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9352. Min Range: -5.9352
Max Act: 5.4352. Min Act: -0.1700
Data Index: 7746962 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9352. Min Range: -5.9352
Max Act: 5.4039. Min Act: -0.1700
Data Index: 1267014 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9352. Min Range: -5.9352
Max Act: 5.4352. Min Act: -0.1700
Data Index: 6803525 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9352. Min Range: -5.9352
Max Act: 5.3727. Min Act: -0.1700
Data Index: 7004730 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9352. Min Range: -5.9352
Max Act: 5.3727. Min Act: -0.1700
Data Index: 2582379 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19