Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2074 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1484. Min Range: -8.1484
Max Act: 8.1484. Min Act: -0.1700
Data Index: 8027120 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1484. Min Range: -8.1484
Max Act: 8.0859. Min Act: -0.1700
Data Index: 7450541 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1484. Min Range: -8.1484
Max Act: 8.0859. Min Act: -0.1700
Data Index: 2422271 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1484. Min Range: -8.1484
Max Act: 7.8984. Min Act: -0.1700
Data Index: 4305813 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1484. Min Range: -8.1484
Max Act: 7.8984. Min Act: -0.1700
Data Index: 4068781 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1484. Min Range: -8.1484
Max Act: 7.8984. Min Act: -0.1700
Data Index: 8392324 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1484. Min Range: -8.1484
Max Act: 7.8359. Min Act: -0.1700
Data Index: 6003678 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1484. Min Range: -8.1484
Max Act: 7.7734. Min Act: -0.1700
Data Index: 4014711 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1484. Min Range: -8.1484
Max Act: 7.7109. Min Act: -0.1700
Data Index: 1571089 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1484. Min Range: -8.1484
Max Act: 7.7109. Min Act: -0.1700
Data Index: 2153048 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1484. Min Range: -8.1484
Max Act: 7.6172. Min Act: -0.1700
Data Index: 633065 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1484. Min Range: -8.1484
Max Act: 7.6172. Min Act: -0.1700
Data Index: 2106456 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1484. Min Range: -8.1484
Max Act: 7.6172. Min Act: -0.1700
Data Index: 4027565 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1484. Min Range: -8.1484
Max Act: 7.5859. Min Act: -0.1700
Data Index: 1656531 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1484. Min Range: -8.1484
Max Act: 7.5547. Min Act: -0.1700
Data Index: 3323626 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1484. Min Range: -8.1484
Max Act: 7.4922. Min Act: -0.1700
Data Index: 8359020 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1484. Min Range: -8.1484
Max Act: 7.5234. Min Act: -0.1700
Data Index: 4852026 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1484. Min Range: -8.1484
Max Act: 7.5234. Min Act: -0.1700
Data Index: 7587023 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1484. Min Range: -8.1484
Max Act: 7.4922. Min Act: -0.1700
Data Index: 6170782 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1484. Min Range: -8.1484
Max Act: 7.4922. Min Act: -0.1700
Data Index: 1957959 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19