Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3423 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8388. Min Range: -5.8388
Max Act: 5.8388. Min Act: -0.1700
Data Index: 3032059 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8388. Min Range: -5.8388
Max Act: 5.7450. Min Act: -0.1700
Data Index: 5213553 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8388. Min Range: -5.8388
Max Act: 5.7138. Min Act: -0.1700
Data Index: 5554698 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8388. Min Range: -5.8388
Max Act: 5.6825. Min Act: -0.1700
Data Index: 8608745 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8388. Min Range: -5.8388
Max Act: 5.6513. Min Act: -0.1700
Data Index: 4260403 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8388. Min Range: -5.8388
Max Act: 5.6200. Min Act: -0.1700
Data Index: 5735783 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8388. Min Range: -5.8388
Max Act: 5.6200. Min Act: -0.1700
Data Index: 3292933 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8388. Min Range: -5.8388
Max Act: 5.6200. Min Act: -0.1700
Data Index: 3032055 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8388. Min Range: -5.8388
Max Act: 5.6200. Min Act: -0.1700
Data Index: 6605708 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8388. Min Range: -5.8388
Max Act: 5.6200. Min Act: -0.1700
Data Index: 8400551 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8388. Min Range: -5.8388
Max Act: 5.5888. Min Act: -0.1700
Data Index: 8824343 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8388. Min Range: -5.8388
Max Act: 5.5575. Min Act: -0.1700
Data Index: 3292935 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8388. Min Range: -5.8388
Max Act: 5.5888. Min Act: -0.1700
Data Index: 4177701 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8388. Min Range: -5.8388
Max Act: 5.5888. Min Act: -0.1700
Data Index: 6689709 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8388. Min Range: -5.8388
Max Act: 5.5575. Min Act: -0.1700
Data Index: 5407509 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8388. Min Range: -5.8388
Max Act: 5.5575. Min Act: -0.1700
Data Index: 7050237 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8388. Min Range: -5.8388
Max Act: 5.5575. Min Act: -0.1700
Data Index: 7687667 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8388. Min Range: -5.8388
Max Act: 5.5575. Min Act: -0.1700
Data Index: 7927016 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8388. Min Range: -5.8388
Max Act: 5.5575. Min Act: -0.1700
Data Index: 8188004 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8388. Min Range: -5.8388
Max Act: 5.5575. Min Act: -0.1700
Data Index: 2311049 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19