Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2354 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5082. Min Range: -6.5082
Max Act: 6.5082. Min Act: -0.1700
Data Index: 5936918 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5082. Min Range: -6.5082
Max Act: 6.1957. Min Act: -0.1700
Data Index: 8602145 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5082. Min Range: -6.5082
Max Act: 6.1957. Min Act: -0.1700
Data Index: 5011411 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5082. Min Range: -6.5082
Max Act: 6.0394. Min Act: -0.1700
Data Index: 533292 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.9457. Min Act: -0.1700
Data Index: 4037342 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5082. Min Range: -6.5082
Max Act: 6.0082. Min Act: -0.1700
Data Index: 2635889 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.9457. Min Act: -0.1700
Data Index: 4595578 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.9144. Min Act: -0.1700
Data Index: 8199545 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.8519. Min Act: -0.1700
Data Index: 6425559 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.9144. Min Act: -0.1700
Data Index: 2565562 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.8207. Min Act: -0.1700
Data Index: 1196778 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.8207. Min Act: -0.1700
Data Index: 6146879 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.7894. Min Act: -0.1700
Data Index: 1773701 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.7894. Min Act: -0.1700
Data Index: 2791389 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.7894. Min Act: -0.1700
Data Index: 8151350 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.7582. Min Act: -0.1700
Data Index: 2537586 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.7582. Min Act: -0.1700
Data Index: 8386449 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.7269. Min Act: -0.1700
Data Index: 6363312 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.7582. Min Act: -0.1700
Data Index: 1053471 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5082. Min Range: -6.5082
Max Act: 5.6957. Min Act: -0.1700
Data Index: 639624 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19