Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6385 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8109. Min Range: -7.8109
Max Act: 7.8109. Min Act: -0.1700
Data Index: 1973122 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8109. Min Range: -7.8109
Max Act: 7.5922. Min Act: -0.1700
Data Index: 770934 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8109. Min Range: -7.8109
Max Act: 7.5609. Min Act: -0.1700
Data Index: 2769780 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8109. Min Range: -7.8109
Max Act: 7.4359. Min Act: -0.1700
Data Index: 2874478 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8109. Min Range: -7.8109
Max Act: 7.4047. Min Act: -0.1700
Data Index: 6576934 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8109. Min Range: -7.8109
Max Act: 7.3109. Min Act: -0.1700
Data Index: 657452 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8109. Min Range: -7.8109
Max Act: 6.9672. Min Act: -0.1700
Data Index: 950439 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8109. Min Range: -7.8109
Max Act: 6.9672. Min Act: -0.1700
Data Index: 2456204 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8109. Min Range: -7.8109
Max Act: 6.9359. Min Act: -0.1700
Data Index: 851275 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8109. Min Range: -7.8109
Max Act: 6.9359. Min Act: -0.1700
Data Index: 4195290 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8109. Min Range: -7.8109
Max Act: 6.9672. Min Act: -0.1700
Data Index: 8770947 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8109. Min Range: -7.8109
Max Act: 6.9359. Min Act: -0.1700
Data Index: 6121571 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8109. Min Range: -7.8109
Max Act: 6.8734. Min Act: -0.1700
Data Index: 6254361 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8109. Min Range: -7.8109
Max Act: 6.8109. Min Act: -0.1700
Data Index: 7295037 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8109. Min Range: -7.8109
Max Act: 6.7797. Min Act: -0.1700
Data Index: 4637778 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8109. Min Range: -7.8109
Max Act: 6.8109. Min Act: -0.1700
Data Index: 5790208 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8109. Min Range: -7.8109
Max Act: 6.7797. Min Act: -0.1700
Data Index: 377141 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8109. Min Range: -7.8109
Max Act: 6.7484. Min Act: -0.1700
Data Index: 5494393 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8109. Min Range: -7.8109
Max Act: 6.7484. Min Act: -0.1700
Data Index: 4281297 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8109. Min Range: -7.8109
Max Act: 6.6859. Min Act: -0.1700
Data Index: 8688114 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19