Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4213 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.6112. Min Act: -0.1700
Data Index: 3680827 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.3612. Min Act: -0.1700
Data Index: 6227388 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.1424. Min Act: -0.1700
Data Index: 3783840 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.1112. Min Act: -0.1700
Data Index: 7156100 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.0799. Min Act: -0.1700
Data Index: 6918777 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.0174. Min Act: -0.1700
Data Index: 8110634 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6112. Min Range: -6.6112
Max Act: 5.9862. Min Act: -0.1700
Data Index: 485444 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6112. Min Range: -6.6112
Max Act: 5.9549. Min Act: -0.1700
Data Index: 2501409 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6112. Min Range: -6.6112
Max Act: 5.9549. Min Act: -0.1700
Data Index: 2351133 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6112. Min Range: -6.6112
Max Act: 5.9549. Min Act: -0.1700
Data Index: 7886486 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6112. Min Range: -6.6112
Max Act: 5.9237. Min Act: -0.1700
Data Index: 7942435 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6112. Min Range: -6.6112
Max Act: 5.8924. Min Act: -0.1700
Data Index: 8786303 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6112. Min Range: -6.6112
Max Act: 5.8612. Min Act: -0.1700
Data Index: 5293838 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6112. Min Range: -6.6112
Max Act: 5.8612. Min Act: -0.1700
Data Index: 2922552 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6112. Min Range: -6.6112
Max Act: 5.8612. Min Act: -0.1700
Data Index: 7182960 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6112. Min Range: -6.6112
Max Act: 5.8612. Min Act: -0.1700
Data Index: 7760467 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6112. Min Range: -6.6112
Max Act: 5.8612. Min Act: -0.1700
Data Index: 4217989 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6112. Min Range: -6.6112
Max Act: 5.8612. Min Act: -0.1700
Data Index: 3018454 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6112. Min Range: -6.6112
Max Act: 5.8299. Min Act: -0.1700
Data Index: 3725527 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6112. Min Range: -6.6112
Max Act: 5.8299. Min Act: -0.1700
Data Index: 878663 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19