Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3884 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.4120. Min Act: -0.1700
Data Index: 3997936 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.4432. Min Act: -0.1700
Data Index: 767952 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.4120. Min Act: -0.1700
Data Index: 6170257 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.4120. Min Act: -0.1700
Data Index: 3696076 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.4120. Min Act: -0.1700
Data Index: 4044642 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.4120. Min Act: -0.1700
Data Index: 3080521 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.3807. Min Act: -0.1700
Data Index: 4929644 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.4120. Min Act: -0.1700
Data Index: 5053550 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.3807. Min Act: -0.1700
Data Index: 6489157 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.3495. Min Act: -0.1700
Data Index: 2850403 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.3807. Min Act: -0.1700
Data Index: 3235 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.3807. Min Act: -0.1700
Data Index: 8680031 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.3807. Min Act: -0.1700
Data Index: 2521070 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.3495. Min Act: -0.1700
Data Index: 7657182 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.3807. Min Act: -0.1700
Data Index: 6797896 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.3807. Min Act: -0.1700
Data Index: 6306223 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.3182. Min Act: -0.1700
Data Index: 969803 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.3807. Min Act: -0.1700
Data Index: 5108500 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.3807. Min Act: -0.1700
Data Index: 4766553 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4432. Min Range: -4.4432
Max Act: 4.3182. Min Act: -0.1700
Data Index: 335727 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19