Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1578 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3662. Min Range: -3.3662
Max Act: 3.3662. Min Act: -0.1700
Data Index: 7982535 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3662. Min Range: -3.3662
Max Act: 3.3035. Min Act: -0.1700
Data Index: 3984979 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3662. Min Range: -3.3662
Max Act: 3.2721. Min Act: -0.1700
Data Index: 5823354 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3662. Min Range: -3.3662
Max Act: 3.2721. Min Act: -0.1700
Data Index: 2916913 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3662. Min Range: -3.3662
Max Act: 3.2721. Min Act: -0.1700
Data Index: 6814125 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3662. Min Range: -3.3662
Max Act: 3.2092. Min Act: -0.1700
Data Index: 7081144 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3662. Min Range: -3.3662
Max Act: 3.2406. Min Act: -0.1700
Data Index: 7397657 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3662. Min Range: -3.3662
Max Act: 3.2406. Min Act: -0.1700
Data Index: 4031837 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3662. Min Range: -3.3662
Max Act: 3.2406. Min Act: -0.1700
Data Index: 7076978 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3662. Min Range: -3.3662
Max Act: 3.2406. Min Act: -0.1700
Data Index: 2679314 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3662. Min Range: -3.3662
Max Act: 3.2406. Min Act: -0.1700
Data Index: 2447208 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3662. Min Range: -3.3662
Max Act: 3.2406. Min Act: -0.1700
Data Index: 1774880 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3662. Min Range: -3.3662
Max Act: 3.2406. Min Act: -0.1700
Data Index: 5963549 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3662. Min Range: -3.3662
Max Act: 3.2092. Min Act: -0.1700
Data Index: 5022936 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3662. Min Range: -3.3662
Max Act: 3.2092. Min Act: -0.1700
Data Index: 6814127 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3662. Min Range: -3.3662
Max Act: 3.2092. Min Act: -0.1700
Data Index: 6990253 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3662. Min Range: -3.3662
Max Act: 3.2092. Min Act: -0.1700
Data Index: 1032671 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3662. Min Range: -3.3662
Max Act: 3.2092. Min Act: -0.1700
Data Index: 4972808 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3662. Min Range: -3.3662
Max Act: 3.2092. Min Act: -0.1700
Data Index: 5508940 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3662. Min Range: -3.3662
Max Act: 3.2092. Min Act: -0.1700
Data Index: 4326755 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19