Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4882 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.0670. Min Range: -10.0670
Max Act: 10.0670. Min Act: -0.1700
Data Index: 1281389 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0670. Min Range: -10.0670
Max Act: 9.8795. Min Act: -0.1700
Data Index: 3325935 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0670. Min Range: -10.0670
Max Act: 9.8795. Min Act: -0.1700
Data Index: 6722301 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0670. Min Range: -10.0670
Max Act: 9.8170. Min Act: -0.1700
Data Index: 5920370 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0670. Min Range: -10.0670
Max Act: 9.8170. Min Act: -0.1700
Data Index: 1612067 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0670. Min Range: -10.0670
Max Act: 9.7545. Min Act: -0.1700
Data Index: 7255655 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0670. Min Range: -10.0670
Max Act: 9.7545. Min Act: -0.1700
Data Index: 233294 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0670. Min Range: -10.0670
Max Act: 9.6920. Min Act: -0.1700
Data Index: 1401889 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0670. Min Range: -10.0670
Max Act: 9.6920. Min Act: -0.1700
Data Index: 2747771 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0670. Min Range: -10.0670
Max Act: 9.6295. Min Act: -0.1700
Data Index: 4898519 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0670. Min Range: -10.0670
Max Act: 9.6295. Min Act: -0.1700
Data Index: 3857730 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0670. Min Range: -10.0670
Max Act: 9.5670. Min Act: -0.1700
Data Index: 2523048 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0670. Min Range: -10.0670
Max Act: 9.5670. Min Act: -0.1700
Data Index: 4357873 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0670. Min Range: -10.0670
Max Act: 9.5670. Min Act: -0.1700
Data Index: 8783111 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0670. Min Range: -10.0670
Max Act: 9.5045. Min Act: -0.1700
Data Index: 6236914 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0670. Min Range: -10.0670
Max Act: 9.5045. Min Act: -0.1700
Data Index: 521595 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0670. Min Range: -10.0670
Max Act: 9.5045. Min Act: -0.1700
Data Index: 4059143 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0670. Min Range: -10.0670
Max Act: 9.4420. Min Act: -0.1700
Data Index: 8513756 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0670. Min Range: -10.0670
Max Act: 9.5045. Min Act: -0.1700
Data Index: 7322649 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0670. Min Range: -10.0670
Max Act: 9.4420. Min Act: -0.1700
Data Index: 5307532 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19