Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3626 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9587. Min Range: -5.9587
Max Act: 5.9587. Min Act: -0.1700
Data Index: 5470468 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9587. Min Range: -5.9587
Max Act: 5.7712. Min Act: -0.1700
Data Index: 4222927 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9587. Min Range: -5.9587
Max Act: 5.7087. Min Act: -0.1700
Data Index: 2294762 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9587. Min Range: -5.9587
Max Act: 5.5837. Min Act: -0.1700
Data Index: 5444255 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9587. Min Range: -5.9587
Max Act: 5.5525. Min Act: -0.1700
Data Index: 3693263 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9587. Min Range: -5.9587
Max Act: 5.5525. Min Act: -0.1700
Data Index: 3935672 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9587. Min Range: -5.9587
Max Act: 5.5212. Min Act: -0.1700
Data Index: 6951055 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9587. Min Range: -5.9587
Max Act: 5.4587. Min Act: -0.1700
Data Index: 3908886 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9587. Min Range: -5.9587
Max Act: 5.4275. Min Act: -0.1700
Data Index: 8363693 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9587. Min Range: -5.9587
Max Act: 5.4275. Min Act: -0.1700
Data Index: 3929709 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9587. Min Range: -5.9587
Max Act: 5.3962. Min Act: -0.1700
Data Index: 6074320 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9587. Min Range: -5.9587
Max Act: 5.3962. Min Act: -0.1700
Data Index: 8303358 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9587. Min Range: -5.9587
Max Act: 5.3650. Min Act: -0.1700
Data Index: 8097818 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9587. Min Range: -5.9587
Max Act: 5.3337. Min Act: -0.1700
Data Index: 1144716 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9587. Min Range: -5.9587
Max Act: 5.3337. Min Act: -0.1700
Data Index: 8073330 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9587. Min Range: -5.9587
Max Act: 5.3025. Min Act: -0.1700
Data Index: 3224941 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9587. Min Range: -5.9587
Max Act: 5.2400. Min Act: -0.1700
Data Index: 269699 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9587. Min Range: -5.9587
Max Act: 5.2400. Min Act: -0.1700
Data Index: 1907776 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9587. Min Range: -5.9587
Max Act: 5.2400. Min Act: -0.1700
Data Index: 6643848 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9587. Min Range: -5.9587
Max Act: 5.2087. Min Act: -0.1700
Data Index: 8552828 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19