Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3019 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2183. Min Range: -7.2183
Max Act: 7.2183. Min Act: -0.1700
Data Index: 2137923 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2183. Min Range: -7.2183
Max Act: 6.9058. Min Act: -0.1700
Data Index: 1329125 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2183. Min Range: -7.2183
Max Act: 6.9058. Min Act: -0.1700
Data Index: 255757 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2183. Min Range: -7.2183
Max Act: 6.8433. Min Act: -0.1700
Data Index: 8369828 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2183. Min Range: -7.2183
Max Act: 6.6870. Min Act: -0.1700
Data Index: 7058457 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2183. Min Range: -7.2183
Max Act: 6.6558. Min Act: -0.1700
Data Index: 1972770 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2183. Min Range: -7.2183
Max Act: 6.5308. Min Act: -0.1700
Data Index: 4389570 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2183. Min Range: -7.2183
Max Act: 6.4370. Min Act: -0.1700
Data Index: 3254487 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2183. Min Range: -7.2183
Max Act: 6.4370. Min Act: -0.1700
Data Index: 5622035 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2183. Min Range: -7.2183
Max Act: 6.3745. Min Act: -0.1700
Data Index: 1610867 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2183. Min Range: -7.2183
Max Act: 6.3120. Min Act: -0.1700
Data Index: 8444176 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2183. Min Range: -7.2183
Max Act: 6.3120. Min Act: -0.1700
Data Index: 1763535 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2183. Min Range: -7.2183
Max Act: 6.3433. Min Act: -0.1700
Data Index: 8186135 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2183. Min Range: -7.2183
Max Act: 6.3120. Min Act: -0.1700
Data Index: 5139820 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2183. Min Range: -7.2183
Max Act: 6.3120. Min Act: -0.1700
Data Index: 337737 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2183. Min Range: -7.2183
Max Act: 6.2808. Min Act: -0.1700
Data Index: 5832391 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2183. Min Range: -7.2183
Max Act: 6.2495. Min Act: -0.1700
Data Index: 7864130 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2183. Min Range: -7.2183
Max Act: 6.2495. Min Act: -0.1700
Data Index: 5622751 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2183. Min Range: -7.2183
Max Act: 6.2183. Min Act: -0.1700
Data Index: 8116396 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2183. Min Range: -7.2183
Max Act: 6.2495. Min Act: -0.1700
Data Index: 4388569 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19