Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5819 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7480. Min Range: -7.7480
Max Act: 7.7480. Min Act: -0.1700
Data Index: 2656795 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7480. Min Range: -7.7480
Max Act: 7.6855. Min Act: -0.1700
Data Index: 7159119 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7480. Min Range: -7.7480
Max Act: 7.6230. Min Act: -0.1700
Data Index: 2269696 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7480. Min Range: -7.7480
Max Act: 7.5293. Min Act: -0.1700
Data Index: 2688375 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7480. Min Range: -7.7480
Max Act: 7.5605. Min Act: -0.1700
Data Index: 6957899 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7480. Min Range: -7.7480
Max Act: 7.6230. Min Act: -0.1700
Data Index: 4514384 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7480. Min Range: -7.7480
Max Act: 7.5293. Min Act: -0.1700
Data Index: 1124818 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7480. Min Range: -7.7480
Max Act: 7.5605. Min Act: -0.1700
Data Index: 7472499 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7480. Min Range: -7.7480
Max Act: 7.5605. Min Act: -0.1700
Data Index: 2611475 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7480. Min Range: -7.7480
Max Act: 7.4980. Min Act: -0.1700
Data Index: 180610 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7480. Min Range: -7.7480
Max Act: 7.4980. Min Act: -0.1700
Data Index: 819104 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7480. Min Range: -7.7480
Max Act: 7.4980. Min Act: -0.1700
Data Index: 8208033 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7480. Min Range: -7.7480
Max Act: 7.4980. Min Act: -0.1700
Data Index: 6501720 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7480. Min Range: -7.7480
Max Act: 7.4980. Min Act: -0.1700
Data Index: 165896 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7480. Min Range: -7.7480
Max Act: 7.4668. Min Act: -0.1700
Data Index: 1580207 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7480. Min Range: -7.7480
Max Act: 7.4980. Min Act: -0.1700
Data Index: 6146731 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7480. Min Range: -7.7480
Max Act: 7.4668. Min Act: -0.1700
Data Index: 6012976 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7480. Min Range: -7.7480
Max Act: 7.4668. Min Act: -0.1700
Data Index: 710897 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7480. Min Range: -7.7480
Max Act: 7.4668. Min Act: -0.1700
Data Index: 1403613 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7480. Min Range: -7.7480
Max Act: 7.4355. Min Act: -0.1700
Data Index: 5593799 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19