Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5295 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6036. Min Range: -4.6036
Max Act: 4.6036. Min Act: -0.1700
Data Index: 5395748 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6036. Min Range: -4.6036
Max Act: 4.3224. Min Act: -0.1700
Data Index: 4427519 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6036. Min Range: -4.6036
Max Act: 4.2911. Min Act: -0.1700
Data Index: 6374912 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6036. Min Range: -4.6036
Max Act: 4.2286. Min Act: -0.1700
Data Index: 8821198 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6036. Min Range: -4.6036
Max Act: 4.1974. Min Act: -0.1700
Data Index: 2875110 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6036. Min Range: -4.6036
Max Act: 4.1974. Min Act: -0.1700
Data Index: 2799688 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6036. Min Range: -4.6036
Max Act: 4.1974. Min Act: -0.1700
Data Index: 2659565 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6036. Min Range: -4.6036
Max Act: 4.1661. Min Act: -0.1700
Data Index: 1705102 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6036. Min Range: -4.6036
Max Act: 4.1349. Min Act: -0.1700
Data Index: 7164901 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6036. Min Range: -4.6036
Max Act: 4.1349. Min Act: -0.1700
Data Index: 7173623 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6036. Min Range: -4.6036
Max Act: 4.1036. Min Act: -0.1700
Data Index: 3508260 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6036. Min Range: -4.6036
Max Act: 4.1036. Min Act: -0.1700
Data Index: 7173622 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6036. Min Range: -4.6036
Max Act: 4.1036. Min Act: -0.1700
Data Index: 123581 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6036. Min Range: -4.6036
Max Act: 4.0411. Min Act: -0.1700
Data Index: 3796117 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6036. Min Range: -4.6036
Max Act: 4.1036. Min Act: -0.1700
Data Index: 6180436 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6036. Min Range: -4.6036
Max Act: 4.0723. Min Act: -0.1700
Data Index: 3979506 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6036. Min Range: -4.6036
Max Act: 4.0723. Min Act: -0.1700
Data Index: 3075427 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6036. Min Range: -4.6036
Max Act: 4.0723. Min Act: -0.1700
Data Index: 4030800 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6036. Min Range: -4.6036
Max Act: 4.0723. Min Act: -0.1700
Data Index: 7169066 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6036. Min Range: -4.6036
Max Act: 4.0411. Min Act: -0.1700
Data Index: 3247438 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19