Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2438 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6830. Min Range: -4.6830
Max Act: 4.6830. Min Act: -0.1700
Data Index: 2078312 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6830. Min Range: -4.6830
Max Act: 4.6517. Min Act: -0.1700
Data Index: 5596828 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6830. Min Range: -4.6830
Max Act: 4.6205. Min Act: -0.1700
Data Index: 4548820 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6830. Min Range: -4.6830
Max Act: 4.5267. Min Act: -0.1700
Data Index: 8009424 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6830. Min Range: -4.6830
Max Act: 4.4955. Min Act: -0.1700
Data Index: 8821477 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6830. Min Range: -4.6830
Max Act: 4.5267. Min Act: -0.1700
Data Index: 1857364 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6830. Min Range: -4.6830
Max Act: 4.4642. Min Act: -0.1700
Data Index: 3900117 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6830. Min Range: -4.6830
Max Act: 4.4642. Min Act: -0.1700
Data Index: 225153 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6830. Min Range: -4.6830
Max Act: 4.4017. Min Act: -0.1700
Data Index: 3090256 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6830. Min Range: -4.6830
Max Act: 4.4330. Min Act: -0.1700
Data Index: 7582463 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6830. Min Range: -4.6830
Max Act: 4.4330. Min Act: -0.1700
Data Index: 8209085 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6830. Min Range: -4.6830
Max Act: 4.3705. Min Act: -0.1700
Data Index: 2078311 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6830. Min Range: -4.6830
Max Act: 4.3705. Min Act: -0.1700
Data Index: 1051263 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6830. Min Range: -4.6830
Max Act: 4.3392. Min Act: -0.1700
Data Index: 5064539 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6830. Min Range: -4.6830
Max Act: 4.3079. Min Act: -0.1700
Data Index: 632490 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6830. Min Range: -4.6830
Max Act: 4.3079. Min Act: -0.1700
Data Index: 7320322 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6830. Min Range: -4.6830
Max Act: 4.3079. Min Act: -0.1700
Data Index: 2878951 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6830. Min Range: -4.6830
Max Act: 4.3079. Min Act: -0.1700
Data Index: 5482512 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6830. Min Range: -4.6830
Max Act: 4.2767. Min Act: -0.1700
Data Index: 6947544 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6830. Min Range: -4.6830
Max Act: 4.2767. Min Act: -0.1700
Data Index: 8025457 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19