Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1816 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3121. Min Range: -9.3121
Max Act: 9.3121. Min Act: -0.1700
Data Index: 306254 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3121. Min Range: -9.3121
Max Act: 9.3121. Min Act: -0.1700
Data Index: 22556 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3121. Min Range: -9.3121
Max Act: 9.1246. Min Act: -0.1700
Data Index: 3162584 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3121. Min Range: -9.3121
Max Act: 9.1246. Min Act: -0.1700
Data Index: 6507358 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3121. Min Range: -9.3121
Max Act: 9.1246. Min Act: -0.1700
Data Index: 3029087 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3121. Min Range: -9.3121
Max Act: 8.9996. Min Act: -0.1700
Data Index: 3730008 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3121. Min Range: -9.3121
Max Act: 8.9996. Min Act: -0.1700
Data Index: 6805303 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3121. Min Range: -9.3121
Max Act: 8.9996. Min Act: -0.1700
Data Index: 1114233 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3121. Min Range: -9.3121
Max Act: 8.9371. Min Act: -0.1700
Data Index: 6678897 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3121. Min Range: -9.3121
Max Act: 8.9371. Min Act: -0.1700
Data Index: 7356391 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3121. Min Range: -9.3121
Max Act: 8.9371. Min Act: -0.1700
Data Index: 7397135 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3121. Min Range: -9.3121
Max Act: 8.9371. Min Act: -0.1700
Data Index: 5855781 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3121. Min Range: -9.3121
Max Act: 8.9371. Min Act: -0.1700
Data Index: 3335185 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3121. Min Range: -9.3121
Max Act: 8.9371. Min Act: -0.1700
Data Index: 4456753 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3121. Min Range: -9.3121
Max Act: 8.8746. Min Act: -0.1700
Data Index: 1755903 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3121. Min Range: -9.3121
Max Act: 8.9371. Min Act: -0.1700
Data Index: 6714022 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3121. Min Range: -9.3121
Max Act: 8.8746. Min Act: -0.1700
Data Index: 8015883 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3121. Min Range: -9.3121
Max Act: 8.8746. Min Act: -0.1700
Data Index: 7384770 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3121. Min Range: -9.3121
Max Act: 8.8121. Min Act: -0.1700
Data Index: 2802281 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3121. Min Range: -9.3121
Max Act: 8.8121. Min Act: -0.1700
Data Index: 3454410 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19