Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3065 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1383. Min Range: -2.1383
Max Act: 2.1216. Min Act: -0.1700
Data Index: 1534332 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1383. Min Range: -2.1383
Max Act: 2.1383. Min Act: -0.1700
Data Index: 3791949 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1383. Min Range: -2.1383
Max Act: 2.0881. Min Act: -0.1700
Data Index: 4015397 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1383. Min Range: -2.1383
Max Act: 2.1048. Min Act: -0.1700
Data Index: 7220976 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1383. Min Range: -2.1383
Max Act: 2.0881. Min Act: -0.1700
Data Index: 6358808 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1383. Min Range: -2.1383
Max Act: 2.0545. Min Act: -0.1700
Data Index: 6928780 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1383. Min Range: -2.1383
Max Act: 2.0545. Min Act: -0.1700
Data Index: 7875815 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1383. Min Range: -2.1383
Max Act: 2.0545. Min Act: -0.1700
Data Index: 6704031 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1383. Min Range: -2.1383
Max Act: 2.0208. Min Act: -0.1700
Data Index: 7594719 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1383. Min Range: -2.1383
Max Act: 2.0377. Min Act: -0.1700
Data Index: 4914113 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1383. Min Range: -2.1383
Max Act: 2.0377. Min Act: -0.1700
Data Index: 5829738 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1383. Min Range: -2.1383
Max Act: 2.0208. Min Act: -0.1700
Data Index: 8453263 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1383. Min Range: -2.1383
Max Act: 2.0208. Min Act: -0.1700
Data Index: 4458818 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1383. Min Range: -2.1383
Max Act: 2.0039. Min Act: -0.1700
Data Index: 4309182 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1383. Min Range: -2.1383
Max Act: 2.0208. Min Act: -0.1700
Data Index: 1361038 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1383. Min Range: -2.1383
Max Act: 2.0039. Min Act: -0.1700
Data Index: 8120867 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1383. Min Range: -2.1383
Max Act: 2.0039. Min Act: -0.1700
Data Index: 5330533 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1383. Min Range: -2.1383
Max Act: 2.0039. Min Act: -0.1695
Data Index: 6775104 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1383. Min Range: -2.1383
Max Act: 1.9870. Min Act: -0.1700
Data Index: 484517 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1383. Min Range: -2.1383
Max Act: 1.9870. Min Act: -0.1700
Data Index: 4580123 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19