Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4171 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4739. Min Range: -5.4739
Max Act: 5.4739. Min Act: -0.1700
Data Index: 2959774 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4739. Min Range: -5.4739
Max Act: 5.4427. Min Act: -0.1700
Data Index: 2929964 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4739. Min Range: -5.4739
Max Act: 5.2552. Min Act: -0.1700
Data Index: 5756265 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4739. Min Range: -5.4739
Max Act: 5.1927. Min Act: -0.1700
Data Index: 8183049 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4739. Min Range: -5.4739
Max Act: 5.2239. Min Act: -0.1700
Data Index: 7970101 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4739. Min Range: -5.4739
Max Act: 5.1927. Min Act: -0.1700
Data Index: 887679 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4739. Min Range: -5.4739
Max Act: 5.1614. Min Act: -0.1700
Data Index: 3528091 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4739. Min Range: -5.4739
Max Act: 5.1927. Min Act: -0.1700
Data Index: 5811257 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4739. Min Range: -5.4739
Max Act: 5.1302. Min Act: -0.1700
Data Index: 5119381 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4739. Min Range: -5.4739
Max Act: 5.1302. Min Act: -0.1700
Data Index: 3613674 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4739. Min Range: -5.4739
Max Act: 5.0989. Min Act: -0.1700
Data Index: 1895995 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4739. Min Range: -5.4739
Max Act: 5.0677. Min Act: -0.1700
Data Index: 8544254 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4739. Min Range: -5.4739
Max Act: 5.0677. Min Act: -0.1700
Data Index: 1175230 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4739. Min Range: -5.4739
Max Act: 5.0677. Min Act: -0.1700
Data Index: 78360 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4739. Min Range: -5.4739
Max Act: 5.0364. Min Act: -0.1700
Data Index: 2074389 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4739. Min Range: -5.4739
Max Act: 5.0364. Min Act: -0.1700
Data Index: 3116489 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4739. Min Range: -5.4739
Max Act: 5.0364. Min Act: -0.1700
Data Index: 4423150 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4739. Min Range: -5.4739
Max Act: 5.0364. Min Act: -0.1700
Data Index: 1177713 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4739. Min Range: -5.4739
Max Act: 5.0052. Min Act: -0.1700
Data Index: 887032 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4739. Min Range: -5.4739
Max Act: 5.0052. Min Act: -0.1700
Data Index: 3598528 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19