Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4385 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6084. Min Range: -4.6084
Max Act: 4.6084. Min Act: -0.1700
Data Index: 8500998 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6084. Min Range: -4.6084
Max Act: 4.3897. Min Act: -0.1700
Data Index: 7181309 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6084. Min Range: -4.6084
Max Act: 4.3897. Min Act: -0.1700
Data Index: 652112 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6084. Min Range: -4.6084
Max Act: 4.3897. Min Act: -0.1700
Data Index: 6967389 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6084. Min Range: -4.6084
Max Act: 4.3584. Min Act: -0.1700
Data Index: 4024521 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6084. Min Range: -4.6084
Max Act: 4.3584. Min Act: -0.1700
Data Index: 4381314 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6084. Min Range: -4.6084
Max Act: 4.3897. Min Act: -0.1700
Data Index: 3231085 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6084. Min Range: -4.6084
Max Act: 4.3584. Min Act: -0.1700
Data Index: 7783609 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6084. Min Range: -4.6084
Max Act: 4.3584. Min Act: -0.1700
Data Index: 6967396 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6084. Min Range: -4.6084
Max Act: 4.3584. Min Act: -0.1700
Data Index: 929159 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6084. Min Range: -4.6084
Max Act: 4.3584. Min Act: -0.1700
Data Index: 2190152 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6084. Min Range: -4.6084
Max Act: 4.3584. Min Act: -0.1700
Data Index: 5636286 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6084. Min Range: -4.6084
Max Act: 4.3272. Min Act: -0.1700
Data Index: 8536198 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6084. Min Range: -4.6084
Max Act: 4.3584. Min Act: -0.1700
Data Index: 8383612 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6084. Min Range: -4.6084
Max Act: 4.3272. Min Act: -0.1700
Data Index: 4244173 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6084. Min Range: -4.6084
Max Act: 4.3272. Min Act: -0.1700
Data Index: 6680231 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6084. Min Range: -4.6084
Max Act: 4.3272. Min Act: -0.1700
Data Index: 6316452 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6084. Min Range: -4.6084
Max Act: 4.3272. Min Act: -0.1700
Data Index: 6015183 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6084. Min Range: -4.6084
Max Act: 4.3272. Min Act: -0.1700
Data Index: 2114817 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6084. Min Range: -4.6084
Max Act: 4.3272. Min Act: -0.1700
Data Index: 283768 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19