Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1740 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0960. Min Range: -6.0960
Max Act: 6.0960. Min Act: -0.1700
Data Index: 802067 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0960. Min Range: -6.0960
Max Act: 5.9397. Min Act: -0.1700
Data Index: 2249695 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0960. Min Range: -6.0960
Max Act: 5.7835. Min Act: -0.1700
Data Index: 1901777 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0960. Min Range: -6.0960
Max Act: 5.7522. Min Act: -0.1700
Data Index: 1274679 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0960. Min Range: -6.0960
Max Act: 5.7522. Min Act: -0.1700
Data Index: 2095650 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0960. Min Range: -6.0960
Max Act: 5.7522. Min Act: -0.1700
Data Index: 7521146 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0960. Min Range: -6.0960
Max Act: 5.6897. Min Act: -0.1700
Data Index: 1954522 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0960. Min Range: -6.0960
Max Act: 5.6585. Min Act: -0.1700
Data Index: 4547066 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0960. Min Range: -6.0960
Max Act: 5.6272. Min Act: -0.1700
Data Index: 3670483 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0960. Min Range: -6.0960
Max Act: 5.6272. Min Act: -0.1700
Data Index: 5804818 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0960. Min Range: -6.0960
Max Act: 5.6272. Min Act: -0.1700
Data Index: 6229498 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0960. Min Range: -6.0960
Max Act: 5.5647. Min Act: -0.1700
Data Index: 6976826 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0960. Min Range: -6.0960
Max Act: 5.5335. Min Act: -0.1700
Data Index: 3405621 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0960. Min Range: -6.0960
Max Act: 5.5022. Min Act: -0.1700
Data Index: 867501 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0960. Min Range: -6.0960
Max Act: 5.5022. Min Act: -0.1700
Data Index: 4613775 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0960. Min Range: -6.0960
Max Act: 5.4710. Min Act: -0.1700
Data Index: 5736929 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0960. Min Range: -6.0960
Max Act: 5.4710. Min Act: -0.1700
Data Index: 2559930 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0960. Min Range: -6.0960
Max Act: 5.4710. Min Act: -0.1700
Data Index: 602155 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0960. Min Range: -6.0960
Max Act: 5.4710. Min Act: -0.1700
Data Index: 6471097 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0960. Min Range: -6.0960
Max Act: 5.4397. Min Act: -0.1700
Data Index: 6103584 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19