Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3169 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0963. Min Range: -6.0963
Max Act: 6.0963. Min Act: -0.1700
Data Index: 6997806 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0963. Min Range: -6.0963
Max Act: 6.0338. Min Act: -0.1700
Data Index: 469566 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0963. Min Range: -6.0963
Max Act: 5.9713. Min Act: -0.1700
Data Index: 3543944 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0963. Min Range: -6.0963
Max Act: 5.9713. Min Act: -0.1700
Data Index: 4016719 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0963. Min Range: -6.0963
Max Act: 5.9400. Min Act: -0.1700
Data Index: 4046517 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0963. Min Range: -6.0963
Max Act: 5.8775. Min Act: -0.1700
Data Index: 184027 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0963. Min Range: -6.0963
Max Act: 5.8775. Min Act: -0.1700
Data Index: 5148626 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0963. Min Range: -6.0963
Max Act: 5.8463. Min Act: -0.1700
Data Index: 1346358 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0963. Min Range: -6.0963
Max Act: 5.8463. Min Act: -0.1700
Data Index: 6737001 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0963. Min Range: -6.0963
Max Act: 5.8463. Min Act: -0.1700
Data Index: 1001947 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0963. Min Range: -6.0963
Max Act: 5.7838. Min Act: -0.1700
Data Index: 5752453 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0963. Min Range: -6.0963
Max Act: 5.7838. Min Act: -0.1700
Data Index: 8559920 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0963. Min Range: -6.0963
Max Act: 5.7525. Min Act: -0.1700
Data Index: 4016717 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0963. Min Range: -6.0963
Max Act: 5.7525. Min Act: -0.1700
Data Index: 5739303 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0963. Min Range: -6.0963
Max Act: 5.7213. Min Act: -0.1700
Data Index: 8519104 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0963. Min Range: -6.0963
Max Act: 5.6900. Min Act: -0.1700
Data Index: 4413593 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0963. Min Range: -6.0963
Max Act: 5.7213. Min Act: -0.1700
Data Index: 3324725 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0963. Min Range: -6.0963
Max Act: 5.6900. Min Act: -0.1700
Data Index: 5885408 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0963. Min Range: -6.0963
Max Act: 5.6588. Min Act: -0.1700
Data Index: 5148627 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0963. Min Range: -6.0963
Max Act: 5.6900. Min Act: -0.1700
Data Index: 5289529 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #19