Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1009 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8565. Min Range: -3.8565
Max Act: 3.8565. Min Act: -0.1700
Data Index: 1247856 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8565. Min Range: -3.8565
Max Act: 3.8252. Min Act: -0.1700
Data Index: 3678875 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8565. Min Range: -3.8565
Max Act: 3.7939. Min Act: -0.1700
Data Index: 2921371 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8565. Min Range: -3.8565
Max Act: 3.7627. Min Act: -0.1700
Data Index: 2949203 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8565. Min Range: -3.8565
Max Act: 3.7627. Min Act: -0.1700
Data Index: 4402139 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8565. Min Range: -3.8565
Max Act: 3.7627. Min Act: -0.1700
Data Index: 3328912 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8565. Min Range: -3.8565
Max Act: 3.7627. Min Act: -0.1700
Data Index: 2810006 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8565. Min Range: -3.8565
Max Act: 3.7314. Min Act: -0.1700
Data Index: 7561348 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8565. Min Range: -3.8565
Max Act: 3.7314. Min Act: -0.1700
Data Index: 630786 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8565. Min Range: -3.8565
Max Act: 3.7627. Min Act: -0.1700
Data Index: 4250199 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8565. Min Range: -3.8565
Max Act: 3.7314. Min Act: -0.1700
Data Index: 4015969 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8565. Min Range: -3.8565
Max Act: 3.7314. Min Act: -0.1700
Data Index: 1764278 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8565. Min Range: -3.8565
Max Act: 3.7001. Min Act: -0.1700
Data Index: 1106215 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8565. Min Range: -3.8565
Max Act: 3.7314. Min Act: -0.1700
Data Index: 3670024 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8565. Min Range: -3.8565
Max Act: 3.7314. Min Act: -0.1700
Data Index: 7784225 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8565. Min Range: -3.8565
Max Act: 3.7314. Min Act: -0.1700
Data Index: 2418225 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8565. Min Range: -3.8565
Max Act: 3.7001. Min Act: -0.1700
Data Index: 3319402 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8565. Min Range: -3.8565
Max Act: 3.7001. Min Act: -0.1700
Data Index: 1317132 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8565. Min Range: -3.8565
Max Act: 3.6688. Min Act: -0.1700
Data Index: 910517 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8565. Min Range: -3.8565
Max Act: 3.7001. Min Act: -0.1700
Data Index: 1127863 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19