Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3821 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8752. Min Range: -1.8752
Max Act: 1.8752. Min Act: -0.1700
Data Index: 7211484 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8752. Min Range: -1.8752
Max Act: 1.8323. Min Act: -0.1700
Data Index: 3016762 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8752. Min Range: -1.8752
Max Act: 1.7290. Min Act: -0.1700
Data Index: 7058326 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8752. Min Range: -1.8752
Max Act: 1.7376. Min Act: -0.1700
Data Index: 7350608 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8752. Min Range: -1.8752
Max Act: 1.7203. Min Act: -0.1700
Data Index: 4764889 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8752. Min Range: -1.8752
Max Act: 1.7116. Min Act: -0.1700
Data Index: 7740938 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8752. Min Range: -1.8752
Max Act: 1.7116. Min Act: -0.1700
Data Index: 261633 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8752. Min Range: -1.8752
Max Act: 1.7030. Min Act: -0.1700
Data Index: 971976 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8752. Min Range: -1.8752
Max Act: 1.6943. Min Act: -0.1700
Data Index: 6336933 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8752. Min Range: -1.8752
Max Act: 1.6943. Min Act: -0.1700
Data Index: 647275 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8752. Min Range: -1.8752
Max Act: 1.6943. Min Act: -0.1700
Data Index: 2656662 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8752. Min Range: -1.8752
Max Act: 1.6943. Min Act: -0.1700
Data Index: 7315369 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8752. Min Range: -1.8752
Max Act: 1.6856. Min Act: -0.1700
Data Index: 4613856 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8752. Min Range: -1.8752
Max Act: 1.6856. Min Act: -0.1700
Data Index: 2100333 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8752. Min Range: -1.8752
Max Act: 1.6856. Min Act: -0.1700
Data Index: 2956762 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8752. Min Range: -1.8752
Max Act: 1.6856. Min Act: -0.1700
Data Index: 6058421 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8752. Min Range: -1.8752
Max Act: 1.6856. Min Act: -0.1700
Data Index: 446047 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8752. Min Range: -1.8752
Max Act: 1.6856. Min Act: -0.1700
Data Index: 3740452 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8752. Min Range: -1.8752
Max Act: 1.6856. Min Act: -0.1700
Data Index: 6962532 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8752. Min Range: -1.8752
Max Act: 1.6769. Min Act: -0.1700
Data Index: 3384935 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19