Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3775 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0848. Min Range: -7.0848
Max Act: 7.0848. Min Act: -0.1700
Data Index: 106226 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0848. Min Range: -7.0848
Max Act: 6.8660. Min Act: -0.1700
Data Index: 2120409 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0848. Min Range: -7.0848
Max Act: 6.7098. Min Act: -0.1700
Data Index: 6124645 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0848. Min Range: -7.0848
Max Act: 6.7410. Min Act: -0.1700
Data Index: 7229208 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0848. Min Range: -7.0848
Max Act: 6.7098. Min Act: -0.1700
Data Index: 6570759 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0848. Min Range: -7.0848
Max Act: 6.6785. Min Act: -0.1700
Data Index: 386614 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0848. Min Range: -7.0848
Max Act: 6.6473. Min Act: -0.1700
Data Index: 2204229 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0848. Min Range: -7.0848
Max Act: 6.6160. Min Act: -0.1700
Data Index: 8093090 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0848. Min Range: -7.0848
Max Act: 6.6160. Min Act: -0.1700
Data Index: 5414610 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0848. Min Range: -7.0848
Max Act: 6.6160. Min Act: -0.1700
Data Index: 5467724 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0848. Min Range: -7.0848
Max Act: 6.6160. Min Act: -0.1700
Data Index: 8221640 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0848. Min Range: -7.0848
Max Act: 6.5535. Min Act: -0.1700
Data Index: 6210491 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0848. Min Range: -7.0848
Max Act: 6.6160. Min Act: -0.1700
Data Index: 993966 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0848. Min Range: -7.0848
Max Act: 6.5223. Min Act: -0.1700
Data Index: 6928742 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0848. Min Range: -7.0848
Max Act: 6.4910. Min Act: -0.1700
Data Index: 4860251 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0848. Min Range: -7.0848
Max Act: 6.5223. Min Act: -0.1700
Data Index: 8074919 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0848. Min Range: -7.0848
Max Act: 6.4910. Min Act: -0.1700
Data Index: 5202669 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0848. Min Range: -7.0848
Max Act: 6.4910. Min Act: -0.1700
Data Index: 6503607 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0848. Min Range: -7.0848
Max Act: 6.4598. Min Act: -0.1700
Data Index: 7907914 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0848. Min Range: -7.0848
Max Act: 6.4598. Min Act: -0.1700
Data Index: 2144257 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19