Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 813 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7485. Min Range: -7.7485
Max Act: 7.7485. Min Act: -0.1700
Data Index: 6505381 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7485. Min Range: -7.7485
Max Act: 7.5922. Min Act: -0.1700
Data Index: 7864675 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7485. Min Range: -7.7485
Max Act: 7.4360. Min Act: -0.1700
Data Index: 7432703 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7485. Min Range: -7.7485
Max Act: 7.4047. Min Act: -0.1700
Data Index: 6120574 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7485. Min Range: -7.7485
Max Act: 7.3422. Min Act: -0.1700
Data Index: 1611417 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7485. Min Range: -7.7485
Max Act: 7.3735. Min Act: -0.1700
Data Index: 3457991 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7485. Min Range: -7.7485
Max Act: 7.3422. Min Act: -0.1700
Data Index: 7926498 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7485. Min Range: -7.7485
Max Act: 7.3110. Min Act: -0.1700
Data Index: 6827001 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7485. Min Range: -7.7485
Max Act: 7.3110. Min Act: -0.1700
Data Index: 3531975 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7485. Min Range: -7.7485
Max Act: 7.2797. Min Act: -0.1700
Data Index: 7923337 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7485. Min Range: -7.7485
Max Act: 7.2797. Min Act: -0.1700
Data Index: 5472026 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7485. Min Range: -7.7485
Max Act: 7.2485. Min Act: -0.1700
Data Index: 3040596 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7485. Min Range: -7.7485
Max Act: 7.2797. Min Act: -0.1700
Data Index: 2216293 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7485. Min Range: -7.7485
Max Act: 7.2172. Min Act: -0.1700
Data Index: 8326386 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7485. Min Range: -7.7485
Max Act: 7.1860. Min Act: -0.1700
Data Index: 1401151 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7485. Min Range: -7.7485
Max Act: 7.1860. Min Act: -0.1700
Data Index: 1679023 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7485. Min Range: -7.7485
Max Act: 7.2172. Min Act: -0.1700
Data Index: 5096923 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7485. Min Range: -7.7485
Max Act: 7.1547. Min Act: -0.1700
Data Index: 7477933 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7485. Min Range: -7.7485
Max Act: 7.1547. Min Act: -0.1700
Data Index: 8696759 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7485. Min Range: -7.7485
Max Act: 7.1547. Min Act: -0.1700
Data Index: 5335211 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19