Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5204 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9304. Min Range: -6.9304
Max Act: 6.9304. Min Act: -0.1700
Data Index: 8793180 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9304. Min Range: -6.9304
Max Act: 6.7429. Min Act: -0.1700
Data Index: 2426725 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9304. Min Range: -6.9304
Max Act: 6.6804. Min Act: -0.1700
Data Index: 4510583 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9304. Min Range: -6.9304
Max Act: 6.6179. Min Act: -0.1700
Data Index: 5679148 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9304. Min Range: -6.9304
Max Act: 6.5242. Min Act: -0.1700
Data Index: 3493356 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9304. Min Range: -6.9304
Max Act: 6.4929. Min Act: -0.1700
Data Index: 5028354 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9304. Min Range: -6.9304
Max Act: 6.4304. Min Act: -0.1700
Data Index: 8793178 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9304. Min Range: -6.9304
Max Act: 6.3679. Min Act: -0.1700
Data Index: 4625934 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9304. Min Range: -6.9304
Max Act: 6.3679. Min Act: -0.1700
Data Index: 3436784 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9304. Min Range: -6.9304
Max Act: 6.3367. Min Act: -0.1700
Data Index: 1667710 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9304. Min Range: -6.9304
Max Act: 6.3054. Min Act: -0.1700
Data Index: 5795106 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9304. Min Range: -6.9304
Max Act: 6.2742. Min Act: -0.1700
Data Index: 6128187 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9304. Min Range: -6.9304
Max Act: 6.2742. Min Act: -0.1700
Data Index: 4949 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9304. Min Range: -6.9304
Max Act: 6.2742. Min Act: -0.1700
Data Index: 6399310 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9304. Min Range: -6.9304
Max Act: 6.2742. Min Act: -0.1700
Data Index: 5276670 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9304. Min Range: -6.9304
Max Act: 6.2742. Min Act: -0.1700
Data Index: 6400667 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9304. Min Range: -6.9304
Max Act: 6.2742. Min Act: -0.1700
Data Index: 5738088 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9304. Min Range: -6.9304
Max Act: 6.2429. Min Act: -0.1700
Data Index: 2478585 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9304. Min Range: -6.9304
Max Act: 6.2429. Min Act: -0.1700
Data Index: 587215 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9304. Min Range: -6.9304
Max Act: 6.2429. Min Act: -0.1700
Data Index: 8004233 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19