Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3778 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7036. Min Range: -8.7036
Max Act: 8.7036. Min Act: -0.1699
Data Index: 56325 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7036. Min Range: -8.7036
Max Act: 8.4536. Min Act: -0.1700
Data Index: 7113190 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7036. Min Range: -8.7036
Max Act: 8.3911. Min Act: -0.1700
Data Index: 1857012 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7036. Min Range: -8.7036
Max Act: 8.3286. Min Act: -0.1700
Data Index: 8615128 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7036. Min Range: -8.7036
Max Act: 8.2661. Min Act: -0.1700
Data Index: 4483089 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7036. Min Range: -8.7036
Max Act: 8.2661. Min Act: -0.1700
Data Index: 4353855 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7036. Min Range: -8.7036
Max Act: 8.2036. Min Act: -0.1700
Data Index: 3216613 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7036. Min Range: -8.7036
Max Act: 8.2036. Min Act: -0.1700
Data Index: 7914350 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7036. Min Range: -8.7036
Max Act: 8.1411. Min Act: -0.1700
Data Index: 4615478 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7036. Min Range: -8.7036
Max Act: 8.2036. Min Act: -0.1700
Data Index: 5905950 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7036. Min Range: -8.7036
Max Act: 8.0474. Min Act: -0.1700
Data Index: 8503383 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7036. Min Range: -8.7036
Max Act: 8.0474. Min Act: -0.1700
Data Index: 7030509 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7036. Min Range: -8.7036
Max Act: 8.0474. Min Act: -0.1700
Data Index: 3157437 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.9849. Min Act: -0.1700
Data Index: 3677413 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.9536. Min Act: -0.1700
Data Index: 3633846 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.9849. Min Act: -0.1700
Data Index: 2771184 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.9536. Min Act: -0.1700
Data Index: 1593361 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.9224. Min Act: -0.1700
Data Index: 3278674 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.9224. Min Act: -0.1700
Data Index: 7237679 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7036. Min Range: -8.7036
Max Act: 7.9224. Min Act: -0.1700
Data Index: 5322568 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19