Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1082 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4820. Min Range: -4.4820
Max Act: 4.4195. Min Act: -0.1700
Data Index: 8113742 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4820. Min Range: -4.4820
Max Act: 4.4820. Min Act: -0.1700
Data Index: 3733007 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4820. Min Range: -4.4820
Max Act: 4.3882. Min Act: -0.1700
Data Index: 5916012 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4820. Min Range: -4.4820
Max Act: 4.3570. Min Act: -0.1700
Data Index: 8649394 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4820. Min Range: -4.4820
Max Act: 4.3570. Min Act: -0.1700
Data Index: 4838820 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4820. Min Range: -4.4820
Max Act: 4.3257. Min Act: -0.1699
Data Index: 4876081 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4820. Min Range: -4.4820
Max Act: 4.2945. Min Act: -0.1699
Data Index: 8653283 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4820. Min Range: -4.4820
Max Act: 4.2945. Min Act: -0.1700
Data Index: 2800490 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4820. Min Range: -4.4820
Max Act: 4.2632. Min Act: -0.1700
Data Index: 7412663 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4820. Min Range: -4.4820
Max Act: 4.1694. Min Act: -0.1700
Data Index: 5128075 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4820. Min Range: -4.4820
Max Act: 4.1694. Min Act: -0.1700
Data Index: 6477844 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4820. Min Range: -4.4820
Max Act: 4.1382. Min Act: -0.1700
Data Index: 6494056 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4820. Min Range: -4.4820
Max Act: 4.2007. Min Act: -0.1700
Data Index: 3421617 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4820. Min Range: -4.4820
Max Act: 4.1382. Min Act: -0.1700
Data Index: 5549048 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4820. Min Range: -4.4820
Max Act: 4.1694. Min Act: -0.1699
Data Index: 99555 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4820. Min Range: -4.4820
Max Act: 4.0757. Min Act: -0.1700
Data Index: 115320 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4820. Min Range: -4.4820
Max Act: 4.1069. Min Act: -0.1700
Data Index: 4763998 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4820. Min Range: -4.4820
Max Act: 4.1069. Min Act: -0.1700
Data Index: 263151 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4820. Min Range: -4.4820
Max Act: 4.1069. Min Act: -0.1699
Data Index: 1868321 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4820. Min Range: -4.4820
Max Act: 4.0757. Min Act: -0.1700
Data Index: 1242769 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19