Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 718 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4129. Min Range: -3.4129
Max Act: 3.4129. Min Act: -0.1700
Data Index: 181676 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4129. Min Range: -3.4129
Max Act: 3.1459. Min Act: -0.1700
Data Index: 1284291 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4129. Min Range: -3.4129
Max Act: 3.0829. Min Act: -0.1700
Data Index: 7020764 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4129. Min Range: -3.4129
Max Act: 3.0513. Min Act: -0.1700
Data Index: 6351245 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4129. Min Range: -3.4129
Max Act: 3.0355. Min Act: -0.1700
Data Index: 477745 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4129. Min Range: -3.4129
Max Act: 3.0197. Min Act: -0.1700
Data Index: 7336644 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4129. Min Range: -3.4129
Max Act: 3.0039. Min Act: -0.1700
Data Index: 802633 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4129. Min Range: -3.4129
Max Act: 2.9881. Min Act: -0.1700
Data Index: 5338544 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4129. Min Range: -3.4129
Max Act: 2.9881. Min Act: -0.1700
Data Index: 2266760 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4129. Min Range: -3.4129
Max Act: 2.9881. Min Act: -0.1700
Data Index: 5460561 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4129. Min Range: -3.4129
Max Act: 2.9881. Min Act: -0.1700
Data Index: 1973144 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4129. Min Range: -3.4129
Max Act: 2.9881. Min Act: -0.1700
Data Index: 5915210 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4129. Min Range: -3.4129
Max Act: 2.9881. Min Act: -0.1700
Data Index: 7399316 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4129. Min Range: -3.4129
Max Act: 2.9565. Min Act: -0.1700
Data Index: 3021823 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4129. Min Range: -3.4129
Max Act: 2.9407. Min Act: -0.1700
Data Index: 4556909 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4129. Min Range: -3.4129
Max Act: 2.9723. Min Act: -0.1700
Data Index: 6068399 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4129. Min Range: -3.4129
Max Act: 2.9565. Min Act: -0.1700
Data Index: 4526142 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4129. Min Range: -3.4129
Max Act: 2.9565. Min Act: -0.1700
Data Index: 4346821 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4129. Min Range: -3.4129
Max Act: 2.9565. Min Act: -0.1700
Data Index: 7830270 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4129. Min Range: -3.4129
Max Act: 2.9407. Min Act: -0.1700
Data Index: 5135625 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19