Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3367 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2500. Min Range: -1.2500
Max Act: 1.2500. Min Act: -0.1699
Data Index: 2687004 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2500. Min Range: -1.2500
Max Act: 1.2324. Min Act: -0.1700
Data Index: 5652440 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2500. Min Range: -1.2500
Max Act: 1.1620. Min Act: -0.1700
Data Index: 3182189 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2500. Min Range: -1.2500
Max Act: 1.1796. Min Act: -0.1700
Data Index: 1664349 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2500. Min Range: -1.2500
Max Act: 1.1620. Min Act: -0.1699
Data Index: 3289152 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2500. Min Range: -1.2500
Max Act: 1.1444. Min Act: -0.1700
Data Index: 8116592 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2500. Min Range: -1.2500
Max Act: 1.1268. Min Act: -0.1696
Data Index: 8469652 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2500. Min Range: -1.2500
Max Act: 1.1444. Min Act: -0.1700
Data Index: 4955966 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2500. Min Range: -1.2500
Max Act: 1.1444. Min Act: -0.1698
Data Index: 2821460 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2500. Min Range: -1.2500
Max Act: 1.1444. Min Act: -0.1700
Data Index: 2297486 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2500. Min Range: -1.2500
Max Act: 1.1268. Min Act: -0.1700
Data Index: 414162 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2500. Min Range: -1.2500
Max Act: 1.1268. Min Act: -0.1700
Data Index: 2567860 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2500. Min Range: -1.2500
Max Act: 1.1093. Min Act: -0.1700
Data Index: 609164 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2500. Min Range: -1.2500
Max Act: 1.1268. Min Act: -0.1700
Data Index: 8036561 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2500. Min Range: -1.2500
Max Act: 1.1268. Min Act: -0.1700
Data Index: 4561227 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2500. Min Range: -1.2500
Max Act: 1.1093. Min Act: -0.1700
Data Index: 791351 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2500. Min Range: -1.2500
Max Act: 1.0918. Min Act: -0.1700
Data Index: 4240892 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2500. Min Range: -1.2500
Max Act: 1.1093. Min Act: -0.1700
Data Index: 1017735 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2500. Min Range: -1.2500
Max Act: 1.0918. Min Act: -0.1700
Data Index: 4116056 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2500. Min Range: -1.2500
Max Act: 1.0918. Min Act: -0.1700
Data Index: 2687005 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19