Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2645 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.3062. Min Range: -8.3062
Max Act: 8.3062. Min Act: -0.1700
Data Index: 8707152 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3062. Min Range: -8.3062
Max Act: 8.1187. Min Act: -0.1700
Data Index: 3338898 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3062. Min Range: -8.3062
Max Act: 7.9937. Min Act: -0.1700
Data Index: 6039017 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3062. Min Range: -8.3062
Max Act: 8.0562. Min Act: -0.1700
Data Index: 8516933 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3062. Min Range: -8.3062
Max Act: 7.9312. Min Act: -0.1700
Data Index: 2073740 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3062. Min Range: -8.3062
Max Act: 7.8374. Min Act: -0.1700
Data Index: 5782583 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3062. Min Range: -8.3062
Max Act: 7.8062. Min Act: -0.1700
Data Index: 7070939 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3062. Min Range: -8.3062
Max Act: 7.7437. Min Act: -0.1700
Data Index: 7197984 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3062. Min Range: -8.3062
Max Act: 7.7437. Min Act: -0.1700
Data Index: 1364246 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3062. Min Range: -8.3062
Max Act: 7.7124. Min Act: -0.1700
Data Index: 1648388 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3062. Min Range: -8.3062
Max Act: 7.6812. Min Act: -0.1700
Data Index: 3355611 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3062. Min Range: -8.3062
Max Act: 7.7124. Min Act: -0.1700
Data Index: 7379781 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3062. Min Range: -8.3062
Max Act: 7.7124. Min Act: -0.1700
Data Index: 2514415 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3062. Min Range: -8.3062
Max Act: 7.6812. Min Act: -0.1700
Data Index: 813850 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3062. Min Range: -8.3062
Max Act: 7.6812. Min Act: -0.1700
Data Index: 4263270 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3062. Min Range: -8.3062
Max Act: 7.6812. Min Act: -0.1700
Data Index: 6308965 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3062. Min Range: -8.3062
Max Act: 7.6499. Min Act: -0.1700
Data Index: 4568012 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3062. Min Range: -8.3062
Max Act: 7.6499. Min Act: -0.1700
Data Index: 4449285 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3062. Min Range: -8.3062
Max Act: 7.5874. Min Act: -0.1700
Data Index: 1782064 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3062. Min Range: -8.3062
Max Act: 7.5874. Min Act: -0.1700
Data Index: 3408622 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19