Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3067 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6641. Min Range: -3.6641
Max Act: 3.6641. Min Act: -0.1700
Data Index: 1352032 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6641. Min Range: -3.6641
Max Act: 3.6485. Min Act: -0.1700
Data Index: 5660145 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6641. Min Range: -3.6641
Max Act: 3.5233. Min Act: -0.1700
Data Index: 2119319 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6641. Min Range: -3.6641
Max Act: 3.4763. Min Act: -0.1700
Data Index: 2921077 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6641. Min Range: -3.6641
Max Act: 3.4293. Min Act: -0.1700
Data Index: 71497 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6641. Min Range: -3.6641
Max Act: 3.3822. Min Act: -0.1700
Data Index: 1224644 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6641. Min Range: -3.6641
Max Act: 3.3822. Min Act: -0.1700
Data Index: 6711250 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6641. Min Range: -3.6641
Max Act: 3.3822. Min Act: -0.1700
Data Index: 115449 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6641. Min Range: -3.6641
Max Act: 3.3666. Min Act: -0.1700
Data Index: 8585596 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6641. Min Range: -3.6641
Max Act: 3.3509. Min Act: -0.1700
Data Index: 4422943 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6641. Min Range: -3.6641
Max Act: 3.3509. Min Act: -0.1700
Data Index: 2308797 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6641. Min Range: -3.6641
Max Act: 3.3509. Min Act: -0.1700
Data Index: 6433606 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6641. Min Range: -3.6641
Max Act: 3.3195. Min Act: -0.1700
Data Index: 8731023 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6641. Min Range: -3.6641
Max Act: 3.3195. Min Act: -0.1700
Data Index: 5258621 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6641. Min Range: -3.6641
Max Act: 3.3195. Min Act: -0.1700
Data Index: 5093199 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6641. Min Range: -3.6641
Max Act: 3.3038. Min Act: -0.1700
Data Index: 6719544 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6641. Min Range: -3.6641
Max Act: 3.2881. Min Act: -0.1700
Data Index: 4312403 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6641. Min Range: -3.6641
Max Act: 3.3038. Min Act: -0.1700
Data Index: 7652357 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6641. Min Range: -3.6641
Max Act: 3.3038. Min Act: -0.1700
Data Index: 3182590 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6641. Min Range: -3.6641
Max Act: 3.3038. Min Act: -0.1700
Data Index: 3403781 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19