Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1961 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0235. Min Range: -6.0235
Max Act: 6.0235. Min Act: -0.1700
Data Index: 112654 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0235. Min Range: -6.0235
Max Act: 5.9610. Min Act: -0.1700
Data Index: 7966751 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0235. Min Range: -6.0235
Max Act: 5.8673. Min Act: -0.1700
Data Index: 4428767 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0235. Min Range: -6.0235
Max Act: 5.7735. Min Act: -0.1700
Data Index: 3551439 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0235. Min Range: -6.0235
Max Act: 5.7423. Min Act: -0.1700
Data Index: 648818 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0235. Min Range: -6.0235
Max Act: 5.6798. Min Act: -0.1700
Data Index: 7791021 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0235. Min Range: -6.0235
Max Act: 5.6798. Min Act: -0.1700
Data Index: 2758319 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0235. Min Range: -6.0235
Max Act: 5.6485. Min Act: -0.1700
Data Index: 8303546 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0235. Min Range: -6.0235
Max Act: 5.6485. Min Act: -0.1700
Data Index: 2103185 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0235. Min Range: -6.0235
Max Act: 5.6173. Min Act: -0.1700
Data Index: 6469856 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0235. Min Range: -6.0235
Max Act: 5.6173. Min Act: -0.1700
Data Index: 5918956 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0235. Min Range: -6.0235
Max Act: 5.6173. Min Act: -0.1700
Data Index: 7120250 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0235. Min Range: -6.0235
Max Act: 5.5860. Min Act: -0.1700
Data Index: 4818532 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0235. Min Range: -6.0235
Max Act: 5.6173. Min Act: -0.1700
Data Index: 7199702 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0235. Min Range: -6.0235
Max Act: 5.6173. Min Act: -0.1700
Data Index: 805600 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0235. Min Range: -6.0235
Max Act: 5.5860. Min Act: -0.1700
Data Index: 4118180 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0235. Min Range: -6.0235
Max Act: 5.5548. Min Act: -0.1700
Data Index: 2289200 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0235. Min Range: -6.0235
Max Act: 5.5548. Min Act: -0.1700
Data Index: 2883631 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0235. Min Range: -6.0235
Max Act: 5.5548. Min Act: -0.1700
Data Index: 279339 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0235. Min Range: -6.0235
Max Act: 5.5548. Min Act: -0.1700
Data Index: 2840444 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #19