Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4546 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2612. Min Range: -6.2612
Max Act: 6.2612. Min Act: -0.1700
Data Index: 7852620 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2612. Min Range: -6.2612
Max Act: 6.2300. Min Act: -0.1700
Data Index: 703377 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2612. Min Range: -6.2612
Max Act: 6.2612. Min Act: -0.1700
Data Index: 532079 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2612. Min Range: -6.2612
Max Act: 6.1675. Min Act: -0.1700
Data Index: 6246549 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2612. Min Range: -6.2612
Max Act: 6.1675. Min Act: -0.1700
Data Index: 533589 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2612. Min Range: -6.2612
Max Act: 6.1362. Min Act: -0.1700
Data Index: 6226599 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2612. Min Range: -6.2612
Max Act: 6.1362. Min Act: -0.1699
Data Index: 3656024 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2612. Min Range: -6.2612
Max Act: 6.0737. Min Act: -0.1700
Data Index: 633144 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2612. Min Range: -6.2612
Max Act: 6.0737. Min Act: -0.1700
Data Index: 7046886 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2612. Min Range: -6.2612
Max Act: 6.1050. Min Act: -0.1700
Data Index: 7356528 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2612. Min Range: -6.2612
Max Act: 6.1050. Min Act: -0.1700
Data Index: 6974585 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2612. Min Range: -6.2612
Max Act: 6.0737. Min Act: -0.1700
Data Index: 6993140 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2612. Min Range: -6.2612
Max Act: 6.0737. Min Act: -0.1700
Data Index: 3107537 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2612. Min Range: -6.2612
Max Act: 6.0737. Min Act: -0.1700
Data Index: 6445006 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2612. Min Range: -6.2612
Max Act: 6.0425. Min Act: -0.1700
Data Index: 106600 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2612. Min Range: -6.2612
Max Act: 6.0425. Min Act: -0.1700
Data Index: 3769918 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2612. Min Range: -6.2612
Max Act: 6.0737. Min Act: -0.1700
Data Index: 7700585 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2612. Min Range: -6.2612
Max Act: 6.0425. Min Act: -0.1700
Data Index: 1078263 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2612. Min Range: -6.2612
Max Act: 6.0112. Min Act: -0.1700
Data Index: 6167362 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2612. Min Range: -6.2612
Max Act: 6.0425. Min Act: -0.1700
Data Index: 4023692 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19