Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1906 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3213. Min Range: -8.3213
Max Act: 8.3213. Min Act: -0.1700
Data Index: 6062674 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3213. Min Range: -8.3213
Max Act: 7.8213. Min Act: -0.1700
Data Index: 2648671 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3213. Min Range: -8.3213
Max Act: 7.7588. Min Act: -0.1700
Data Index: 6780325 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3213. Min Range: -8.3213
Max Act: 7.7588. Min Act: -0.1700
Data Index: 4473121 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3213. Min Range: -8.3213
Max Act: 7.6963. Min Act: -0.1700
Data Index: 2899994 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3213. Min Range: -8.3213
Max Act: 7.7588. Min Act: -0.1700
Data Index: 7275691 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3213. Min Range: -8.3213
Max Act: 7.6338. Min Act: -0.1700
Data Index: 3086483 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3213. Min Range: -8.3213
Max Act: 7.6338. Min Act: -0.1700
Data Index: 2509604 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3213. Min Range: -8.3213
Max Act: 7.6338. Min Act: -0.1700
Data Index: 2983905 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3213. Min Range: -8.3213
Max Act: 7.5713. Min Act: -0.1700
Data Index: 3662361 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3213. Min Range: -8.3213
Max Act: 7.5713. Min Act: -0.1700
Data Index: 6780324 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3213. Min Range: -8.3213
Max Act: 7.5088. Min Act: -0.1700
Data Index: 8154629 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3213. Min Range: -8.3213
Max Act: 7.5713. Min Act: -0.1700
Data Index: 7739417 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3213. Min Range: -8.3213
Max Act: 7.5713. Min Act: -0.1700
Data Index: 421729 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3213. Min Range: -8.3213
Max Act: 7.5713. Min Act: -0.1700
Data Index: 2983901 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3213. Min Range: -8.3213
Max Act: 7.5713. Min Act: -0.1700
Data Index: 3086486 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3213. Min Range: -8.3213
Max Act: 7.5088. Min Act: -0.1700
Data Index: 7739414 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3213. Min Range: -8.3213
Max Act: 7.5088. Min Act: -0.1700
Data Index: 6878856 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3213. Min Range: -8.3213
Max Act: 7.4776. Min Act: -0.1700
Data Index: 3392035 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3213. Min Range: -8.3213
Max Act: 7.4463. Min Act: -0.1700
Data Index: 599092 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19