Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4204 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2286. Min Range: -3.2286
Max Act: 3.2286. Min Act: -0.1700
Data Index: 369943 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2286. Min Range: -3.2286
Max Act: 2.9606. Min Act: -0.1700
Data Index: 3268525 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2286. Min Range: -3.2286
Max Act: 2.9448. Min Act: -0.1700
Data Index: 4419323 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2286. Min Range: -3.2286
Max Act: 2.9131. Min Act: -0.1700
Data Index: 1560045 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2286. Min Range: -3.2286
Max Act: 2.8973. Min Act: -0.1700
Data Index: 8562182 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2286. Min Range: -3.2286
Max Act: 2.8814. Min Act: -0.1700
Data Index: 1515715 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2286. Min Range: -3.2286
Max Act: 2.8496. Min Act: -0.1700
Data Index: 6649763 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2286. Min Range: -3.2286
Max Act: 2.8496. Min Act: -0.1700
Data Index: 3628344 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2286. Min Range: -3.2286
Max Act: 2.8178. Min Act: -0.1700
Data Index: 2049216 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2286. Min Range: -3.2286
Max Act: 2.8178. Min Act: -0.1700
Data Index: 3628342 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2286. Min Range: -3.2286
Max Act: 2.7860. Min Act: -0.1700
Data Index: 7925964 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2286. Min Range: -3.2286
Max Act: 2.7700. Min Act: -0.1700
Data Index: 8370123 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2286. Min Range: -3.2286
Max Act: 2.7700. Min Act: -0.1700
Data Index: 3268521 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2286. Min Range: -3.2286
Max Act: 2.7541. Min Act: -0.1700
Data Index: 3785291 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2286. Min Range: -3.2286
Max Act: 2.7541. Min Act: -0.1700
Data Index: 3630528 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2286. Min Range: -3.2286
Max Act: 2.7541. Min Act: -0.1700
Data Index: 470774 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2286. Min Range: -3.2286
Max Act: 2.7381. Min Act: -0.1700
Data Index: 1550458 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2286. Min Range: -3.2286
Max Act: 2.7541. Min Act: -0.1700
Data Index: 5967528 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2286. Min Range: -3.2286
Max Act: 2.7541. Min Act: -0.1700
Data Index: 6011002 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2286. Min Range: -3.2286
Max Act: 2.7541. Min Act: -0.1700
Data Index: 7325599 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19