Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1357 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.6297. Min Act: -0.1700
Data Index: 5845954 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.5814. Min Act: -0.1700
Data Index: 5765773 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.5814. Min Act: -0.1680
Data Index: 6517774 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.5491. Min Act: -0.1699
Data Index: 5179739 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.5330. Min Act: -0.1700
Data Index: 3166662 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.5330. Min Act: -0.1700
Data Index: 4866089 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.5168. Min Act: -0.1700
Data Index: 6441744 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.5006. Min Act: -0.1674
Data Index: 6322271 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4682. Min Act: -0.1694
Data Index: 977956 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4844. Min Act: -0.1522
Data Index: 6597391 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4844. Min Act: -0.1697
Data Index: 2516374 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4682. Min Act: -0.1686
Data Index: 8139286 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4844. Min Act: -0.1700
Data Index: 3682000 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4844. Min Act: -0.1599
Data Index: 7748385 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4844. Min Act: -0.1700
Data Index: 6776093 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4844. Min Act: -0.1699
Data Index: 3520080 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4682. Min Act: -0.1700
Data Index: 604895 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4519. Min Act: -0.1683
Data Index: 1639213 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4519. Min Act: -0.1697
Data Index: 1210951 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6297. Min Range: -2.6297
Max Act: 2.4357. Min Act: -0.1700
Data Index: 4255161 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19