Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4378 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7337. Min Range: -5.7337
Max Act: 5.7337. Min Act: -0.1700
Data Index: 3083912 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7337. Min Range: -5.7337
Max Act: 5.2337. Min Act: -0.1700
Data Index: 1272312 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7337. Min Range: -5.7337
Max Act: 5.2024. Min Act: -0.1700
Data Index: 488548 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7337. Min Range: -5.7337
Max Act: 5.0149. Min Act: -0.1700
Data Index: 3770657 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7337. Min Range: -5.7337
Max Act: 4.9212. Min Act: -0.1700
Data Index: 3962401 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7337. Min Range: -5.7337
Max Act: 4.9212. Min Act: -0.1700
Data Index: 8297766 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7337. Min Range: -5.7337
Max Act: 4.8587. Min Act: -0.1700
Data Index: 3770656 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7337. Min Range: -5.7337
Max Act: 4.8587. Min Act: -0.1700
Data Index: 8635902 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7337. Min Range: -5.7337
Max Act: 4.8274. Min Act: -0.1700
Data Index: 1335530 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7337. Min Range: -5.7337
Max Act: 4.7962. Min Act: -0.1700
Data Index: 2991686 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7337. Min Range: -5.7337
Max Act: 4.7962. Min Act: -0.1700
Data Index: 2543375 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7337. Min Range: -5.7337
Max Act: 4.7962. Min Act: -0.1700
Data Index: 6613044 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7337. Min Range: -5.7337
Max Act: 4.7962. Min Act: -0.1700
Data Index: 6725299 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7337. Min Range: -5.7337
Max Act: 4.7649. Min Act: -0.1700
Data Index: 7360972 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7337. Min Range: -5.7337
Max Act: 4.7962. Min Act: -0.1700
Data Index: 6458159 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7337. Min Range: -5.7337
Max Act: 4.7337. Min Act: -0.1700
Data Index: 1335719 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7337. Min Range: -5.7337
Max Act: 4.7024. Min Act: -0.1700
Data Index: 3220260 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7337. Min Range: -5.7337
Max Act: 4.7024. Min Act: -0.1700
Data Index: 6758083 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7337. Min Range: -5.7337
Max Act: 4.7024. Min Act: -0.1700
Data Index: 1335541 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7337. Min Range: -5.7337
Max Act: 4.6712. Min Act: -0.1700
Data Index: 6597517 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19