Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3303 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.8754. Min Act: -0.1700
Data Index: 4472298 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.8128. Min Act: -0.1700
Data Index: 3975984 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.7503. Min Act: -0.1700
Data Index: 3660030 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.6877. Min Act: -0.1700
Data Index: 7461516 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.5782. Min Act: -0.1700
Data Index: 2280651 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.5625. Min Act: -0.1700
Data Index: 5030876 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.5469. Min Act: -0.1700
Data Index: 2564236 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.4842. Min Act: -0.1700
Data Index: 7675824 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.4372. Min Act: -0.1700
Data Index: 3842293 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.4529. Min Act: -0.1700
Data Index: 238835 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.4372. Min Act: -0.1700
Data Index: 5908208 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.4529. Min Act: -0.1700
Data Index: 238830 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.4215. Min Act: -0.1700
Data Index: 6685777 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.4215. Min Act: -0.1700
Data Index: 1309032 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.4372. Min Act: -0.1700
Data Index: 8217138 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.4059. Min Act: -0.1700
Data Index: 4453584 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.4059. Min Act: -0.1700
Data Index: 2884086 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.4059. Min Act: -0.1700
Data Index: 540899 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.3902. Min Act: -0.1700
Data Index: 4231729 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8754. Min Range: -3.8754
Max Act: 3.3588. Min Act: -0.1700
Data Index: 4705721 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19