Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4604 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3674. Min Range: -5.3674
Max Act: 5.3674. Min Act: -0.1700
Data Index: 8738306 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3674. Min Range: -5.3674
Max Act: 5.3674. Min Act: -0.1700
Data Index: 4651047 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3674. Min Range: -5.3674
Max Act: 5.3362. Min Act: -0.1700
Data Index: 2575787 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3674. Min Range: -5.3674
Max Act: 5.2424. Min Act: -0.1700
Data Index: 4197840 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3674. Min Range: -5.3674
Max Act: 5.2424. Min Act: -0.1700
Data Index: 4656596 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3674. Min Range: -5.3674
Max Act: 5.2424. Min Act: -0.1700
Data Index: 8614651 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3674. Min Range: -5.3674
Max Act: 5.1487. Min Act: -0.1700
Data Index: 7499 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3674. Min Range: -5.3674
Max Act: 5.1487. Min Act: -0.1700
Data Index: 1190507 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3674. Min Range: -5.3674
Max Act: 5.1487. Min Act: -0.1700
Data Index: 6434506 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3674. Min Range: -5.3674
Max Act: 5.1487. Min Act: -0.1700
Data Index: 4491634 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3674. Min Range: -5.3674
Max Act: 5.1487. Min Act: -0.1700
Data Index: 6168743 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3674. Min Range: -5.3674
Max Act: 5.1174. Min Act: -0.1700
Data Index: 6517202 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3674. Min Range: -5.3674
Max Act: 5.1174. Min Act: -0.1700
Data Index: 7644226 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3674. Min Range: -5.3674
Max Act: 5.1174. Min Act: -0.1700
Data Index: 6434494 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3674. Min Range: -5.3674
Max Act: 5.1174. Min Act: -0.1700
Data Index: 769077 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3674. Min Range: -5.3674
Max Act: 5.0862. Min Act: -0.1700
Data Index: 3870646 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3674. Min Range: -5.3674
Max Act: 5.1174. Min Act: -0.1700
Data Index: 7734423 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3674. Min Range: -5.3674
Max Act: 5.1174. Min Act: -0.1700
Data Index: 699515 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3674. Min Range: -5.3674
Max Act: 5.1174. Min Act: -0.1700
Data Index: 917900 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3674. Min Range: -5.3674
Max Act: 5.1174. Min Act: -0.1700
Data Index: 4097622 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19