Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3306 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7899. Min Range: -1.7899
Max Act: 1.7899. Min Act: -0.1700
Data Index: 2314009 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7899. Min Range: -1.7899
Max Act: 1.7468. Min Act: -0.1700
Data Index: 8577940 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7899. Min Range: -1.7899
Max Act: 1.7295. Min Act: -0.1697
Data Index: 3519558 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7899. Min Range: -1.7899
Max Act: 1.7381. Min Act: -0.1700
Data Index: 7006139 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7899. Min Range: -1.7899
Max Act: 1.6862. Min Act: -0.1700
Data Index: 5829604 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7899. Min Range: -1.7899
Max Act: 1.6775. Min Act: -0.1700
Data Index: 1043427 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7899. Min Range: -1.7899
Max Act: 1.6688. Min Act: -0.1700
Data Index: 8599545 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7899. Min Range: -1.7899
Max Act: 1.6601. Min Act: -0.1700
Data Index: 6847797 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7899. Min Range: -1.7899
Max Act: 1.6165. Min Act: -0.1700
Data Index: 8103631 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7899. Min Range: -1.7899
Max Act: 1.6078. Min Act: -0.1700
Data Index: 5450146 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7899. Min Range: -1.7899
Max Act: 1.6078. Min Act: -0.1700
Data Index: 8722029 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7899. Min Range: -1.7899
Max Act: 1.5991. Min Act: -0.1700
Data Index: 6075848 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7899. Min Range: -1.7899
Max Act: 1.5991. Min Act: -0.1700
Data Index: 983293 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7899. Min Range: -1.7899
Max Act: 1.6078. Min Act: -0.1700
Data Index: 7626409 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7899. Min Range: -1.7899
Max Act: 1.5904. Min Act: -0.1699
Data Index: 6250441 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7899. Min Range: -1.7899
Max Act: 1.5904. Min Act: -0.1697
Data Index: 1498652 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7899. Min Range: -1.7899
Max Act: 1.5904. Min Act: -0.1700
Data Index: 7456651 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7899. Min Range: -1.7899
Max Act: 1.5904. Min Act: -0.1700
Data Index: 4004031 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7899. Min Range: -1.7899
Max Act: 1.5816. Min Act: -0.1700
Data Index: 3755219 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7899. Min Range: -1.7899
Max Act: 1.5816. Min Act: -0.1695
Data Index: 2009888 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19