Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1237 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7090. Min Range: -4.7090
Max Act: 4.7090. Min Act: -0.1700
Data Index: 559255 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7090. Min Range: -4.7090
Max Act: 4.3340. Min Act: -0.1700
Data Index: 2288313 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7090. Min Range: -4.7090
Max Act: 4.2715. Min Act: -0.1700
Data Index: 6563665 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7090. Min Range: -4.7090
Max Act: 4.3028. Min Act: -0.1700
Data Index: 4630648 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7090. Min Range: -4.7090
Max Act: 4.2403. Min Act: -0.1700
Data Index: 6824346 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7090. Min Range: -4.7090
Max Act: 4.2403. Min Act: -0.1700
Data Index: 41050 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7090. Min Range: -4.7090
Max Act: 4.2090. Min Act: -0.1700
Data Index: 8210405 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7090. Min Range: -4.7090
Max Act: 4.1778. Min Act: -0.1700
Data Index: 4772123 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7090. Min Range: -4.7090
Max Act: 4.2090. Min Act: -0.1700
Data Index: 8707156 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7090. Min Range: -4.7090
Max Act: 4.1778. Min Act: -0.1700
Data Index: 7787467 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7090. Min Range: -4.7090
Max Act: 4.1465. Min Act: -0.1700
Data Index: 2484088 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7090. Min Range: -4.7090
Max Act: 4.1465. Min Act: -0.1700
Data Index: 1349936 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7090. Min Range: -4.7090
Max Act: 4.1778. Min Act: -0.1700
Data Index: 6689033 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7090. Min Range: -4.7090
Max Act: 4.1465. Min Act: -0.1700
Data Index: 2451891 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7090. Min Range: -4.7090
Max Act: 4.1465. Min Act: -0.1700
Data Index: 796817 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7090. Min Range: -4.7090
Max Act: 4.1152. Min Act: -0.1700
Data Index: 4127641 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7090. Min Range: -4.7090
Max Act: 4.0840. Min Act: -0.1700
Data Index: 601590 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7090. Min Range: -4.7090
Max Act: 4.1152. Min Act: -0.1700
Data Index: 6669751 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7090. Min Range: -4.7090
Max Act: 4.1152. Min Act: -0.1700
Data Index: 802909 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7090. Min Range: -4.7090
Max Act: 4.1152. Min Act: -0.1700
Data Index: 4058270 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19