Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4392 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4586. Min Range: -5.4586
Max Act: 5.4586. Min Act: -0.1700
Data Index: 6091852 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4586. Min Range: -5.4586
Max Act: 5.4273. Min Act: -0.1700
Data Index: 5545628 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4586. Min Range: -5.4586
Max Act: 5.3961. Min Act: -0.1700
Data Index: 8796329 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4586. Min Range: -5.4586
Max Act: 5.3648. Min Act: -0.1700
Data Index: 1429537 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4586. Min Range: -5.4586
Max Act: 5.3023. Min Act: -0.1700
Data Index: 4480600 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4586. Min Range: -5.4586
Max Act: 5.2711. Min Act: -0.1700
Data Index: 4366201 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4586. Min Range: -5.4586
Max Act: 5.2711. Min Act: -0.1700
Data Index: 4466957 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4586. Min Range: -5.4586
Max Act: 5.2711. Min Act: -0.1700
Data Index: 512711 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4586. Min Range: -5.4586
Max Act: 5.2086. Min Act: -0.1700
Data Index: 3800802 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4586. Min Range: -5.4586
Max Act: 5.1773. Min Act: -0.1700
Data Index: 5903777 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4586. Min Range: -5.4586
Max Act: 5.1773. Min Act: -0.1700
Data Index: 7576389 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4586. Min Range: -5.4586
Max Act: 5.1773. Min Act: -0.1700
Data Index: 5777039 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4586. Min Range: -5.4586
Max Act: 5.1461. Min Act: -0.1700
Data Index: 3668474 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4586. Min Range: -5.4586
Max Act: 5.1461. Min Act: -0.1700
Data Index: 2150475 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4586. Min Range: -5.4586
Max Act: 5.1148. Min Act: -0.1700
Data Index: 3933618 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4586. Min Range: -5.4586
Max Act: 5.1148. Min Act: -0.1700
Data Index: 6494087 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4586. Min Range: -5.4586
Max Act: 5.0836. Min Act: -0.1700
Data Index: 7085485 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4586. Min Range: -5.4586
Max Act: 5.1148. Min Act: -0.1700
Data Index: 3008683 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4586. Min Range: -5.4586
Max Act: 5.1148. Min Act: -0.1700
Data Index: 7050562 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4586. Min Range: -5.4586
Max Act: 5.0836. Min Act: -0.1700
Data Index: 6036035 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19