Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5102 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2617. Min Range: -6.2617
Max Act: 6.2617. Min Act: -0.1700
Data Index: 5636026 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2617. Min Range: -6.2617
Max Act: 6.1992. Min Act: -0.1700
Data Index: 8520064 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2617. Min Range: -6.2617
Max Act: 6.1054. Min Act: -0.1700
Data Index: 3460733 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2617. Min Range: -6.2617
Max Act: 6.1054. Min Act: -0.1700
Data Index: 5150291 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2617. Min Range: -6.2617
Max Act: 6.0429. Min Act: -0.1700
Data Index: 2193506 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2617. Min Range: -6.2617
Max Act: 6.0429. Min Act: -0.1700
Data Index: 588108 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2617. Min Range: -6.2617
Max Act: 6.0117. Min Act: -0.1700
Data Index: 5780050 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2617. Min Range: -6.2617
Max Act: 6.0117. Min Act: -0.1700
Data Index: 7359258 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2617. Min Range: -6.2617
Max Act: 6.0117. Min Act: -0.1700
Data Index: 3673240 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.9804. Min Act: -0.1700
Data Index: 2005308 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.9492. Min Act: -0.1700
Data Index: 7184667 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.9804. Min Act: -0.1700
Data Index: 3046284 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.9804. Min Act: -0.1700
Data Index: 677393 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.9179. Min Act: -0.1700
Data Index: 4877680 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.9179. Min Act: -0.1700
Data Index: 4477344 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.9492. Min Act: -0.1700
Data Index: 3157127 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.8867. Min Act: -0.1700
Data Index: 5522146 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.9179. Min Act: -0.1700
Data Index: 3021716 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.9179. Min Act: -0.1700
Data Index: 8230609 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2617. Min Range: -6.2617
Max Act: 5.8867. Min Act: -0.1700
Data Index: 4745503 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19