Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3041 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3330. Min Range: -5.3330
Max Act: 5.3018. Min Act: -0.1700
Data Index: 5510528 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3330. Min Range: -5.3330
Max Act: 5.3330. Min Act: -0.1700
Data Index: 3874831 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3330. Min Range: -5.3330
Max Act: 5.3018. Min Act: -0.1700
Data Index: 8458412 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3330. Min Range: -5.3330
Max Act: 5.2393. Min Act: -0.1700
Data Index: 2637233 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3330. Min Range: -5.3330
Max Act: 5.2393. Min Act: -0.1700
Data Index: 4984761 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3330. Min Range: -5.3330
Max Act: 5.2080. Min Act: -0.1700
Data Index: 5147527 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3330. Min Range: -5.3330
Max Act: 5.2080. Min Act: -0.1700
Data Index: 4680829 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3330. Min Range: -5.3330
Max Act: 5.1768. Min Act: -0.1700
Data Index: 4191030 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3330. Min Range: -5.3330
Max Act: 5.1143. Min Act: -0.1700
Data Index: 5430804 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3330. Min Range: -5.3330
Max Act: 5.1455. Min Act: -0.1700
Data Index: 332326 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3330. Min Range: -5.3330
Max Act: 5.1455. Min Act: -0.1700
Data Index: 7125398 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3330. Min Range: -5.3330
Max Act: 5.1143. Min Act: -0.1700
Data Index: 286470 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3330. Min Range: -5.3330
Max Act: 5.1143. Min Act: -0.1700
Data Index: 2292198 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3330. Min Range: -5.3330
Max Act: 5.1455. Min Act: -0.1700
Data Index: 492892 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3330. Min Range: -5.3330
Max Act: 5.0830. Min Act: -0.1700
Data Index: 1266295 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3330. Min Range: -5.3330
Max Act: 5.0830. Min Act: -0.1700
Data Index: 47375 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3330. Min Range: -5.3330
Max Act: 5.0830. Min Act: -0.1700
Data Index: 725604 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3330. Min Range: -5.3330
Max Act: 5.0518. Min Act: -0.1700
Data Index: 6647102 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3330. Min Range: -5.3330
Max Act: 5.0205. Min Act: -0.1700
Data Index: 6822338 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3330. Min Range: -5.3330
Max Act: 5.0518. Min Act: -0.1700
Data Index: 2034530 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19