Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.6594. Min Act: -0.1700
Data Index: 3217427 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.3469. Min Act: -0.1700
Data Index: 1401111 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.2844. Min Act: -0.1700
Data Index: 4988295 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.2531. Min Act: -0.1700
Data Index: 5095086 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.2219. Min Act: -0.1700
Data Index: 1091120 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.2531. Min Act: -0.1700
Data Index: 7682233 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.2219. Min Act: -0.1700
Data Index: 2400957 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.2219. Min Act: -0.1700
Data Index: 1076141 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.2219. Min Act: -0.1700
Data Index: 2853429 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.1906. Min Act: -0.1700
Data Index: 691592 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.1906. Min Act: -0.1699
Data Index: 7779997 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.1906. Min Act: -0.1700
Data Index: 6750152 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.1906. Min Act: -0.1700
Data Index: 3226362 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.1594. Min Act: -0.1700
Data Index: 3440552 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.1594. Min Act: -0.1700
Data Index: 3010173 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.1594. Min Act: -0.1700
Data Index: 7259128 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.0656. Min Act: -0.1700
Data Index: 4796007 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.1281. Min Act: -0.1700
Data Index: 772576 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.1594. Min Act: -0.1700
Data Index: 4862483 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6594. Min Range: -4.6594
Max Act: 4.0968. Min Act: -0.1700
Data Index: 4169413 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19