Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3384 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9033. Min Range: -6.9033
Max Act: 6.9033. Min Act: -0.1700
Data Index: 1273542 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9033. Min Range: -6.9033
Max Act: 5.6533. Min Act: -0.1700
Data Index: 6514724 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9033. Min Range: -6.9033
Max Act: 5.6220. Min Act: -0.1700
Data Index: 6082676 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9033. Min Range: -6.9033
Max Act: 5.5595. Min Act: -0.1700
Data Index: 8382835 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9033. Min Range: -6.9033
Max Act: 5.5283. Min Act: -0.1700
Data Index: 2695209 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9033. Min Range: -6.9033
Max Act: 5.5595. Min Act: -0.1700
Data Index: 4515238 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9033. Min Range: -6.9033
Max Act: 5.5283. Min Act: -0.1700
Data Index: 2661105 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9033. Min Range: -6.9033
Max Act: 5.5283. Min Act: -0.1700
Data Index: 2957720 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9033. Min Range: -6.9033
Max Act: 5.5283. Min Act: -0.1700
Data Index: 4042479 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9033. Min Range: -6.9033
Max Act: 5.5283. Min Act: -0.1700
Data Index: 8142703 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9033. Min Range: -6.9033
Max Act: 5.4970. Min Act: -0.1700
Data Index: 2629278 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9033. Min Range: -6.9033
Max Act: 5.4658. Min Act: -0.1700
Data Index: 1378830 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9033. Min Range: -6.9033
Max Act: 5.4658. Min Act: -0.1700
Data Index: 2383294 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9033. Min Range: -6.9033
Max Act: 5.4345. Min Act: -0.1700
Data Index: 5300253 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9033. Min Range: -6.9033
Max Act: 5.4658. Min Act: -0.1700
Data Index: 3944098 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9033. Min Range: -6.9033
Max Act: 5.4345. Min Act: -0.1700
Data Index: 298499 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9033. Min Range: -6.9033
Max Act: 5.4345. Min Act: -0.1700
Data Index: 298170 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9033. Min Range: -6.9033
Max Act: 5.4345. Min Act: -0.1700
Data Index: 64368 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9033. Min Range: -6.9033
Max Act: 5.3720. Min Act: -0.1700
Data Index: 2196503 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9033. Min Range: -6.9033
Max Act: 5.4033. Min Act: -0.1700
Data Index: 5897157 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19