Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1646 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9427. Min Range: -3.9427
Max Act: 3.9427. Min Act: -0.1700
Data Index: 2213291 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9427. Min Range: -3.9427
Max Act: 3.8802. Min Act: -0.1700
Data Index: 7972641 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9427. Min Range: -3.9427
Max Act: 3.8489. Min Act: -0.1700
Data Index: 7694146 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9427. Min Range: -3.9427
Max Act: 3.8489. Min Act: -0.1700
Data Index: 996739 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9427. Min Range: -3.9427
Max Act: 3.8489. Min Act: -0.1700
Data Index: 3559754 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9427. Min Range: -3.9427
Max Act: 3.8802. Min Act: -0.1700
Data Index: 8466322 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9427. Min Range: -3.9427
Max Act: 3.8489. Min Act: -0.1700
Data Index: 3053624 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9427. Min Range: -3.9427
Max Act: 3.8176. Min Act: -0.1700
Data Index: 810405 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9427. Min Range: -3.9427
Max Act: 3.8176. Min Act: -0.1700
Data Index: 1941456 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9427. Min Range: -3.9427
Max Act: 3.8176. Min Act: -0.1700
Data Index: 3484072 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9427. Min Range: -3.9427
Max Act: 3.8176. Min Act: -0.1700
Data Index: 2067034 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9427. Min Range: -3.9427
Max Act: 3.8176. Min Act: -0.1700
Data Index: 728691 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9427. Min Range: -3.9427
Max Act: 3.8176. Min Act: -0.1700
Data Index: 2380881 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9427. Min Range: -3.9427
Max Act: 3.8176. Min Act: -0.1700
Data Index: 3762312 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9427. Min Range: -3.9427
Max Act: 3.8176. Min Act: -0.1700
Data Index: 4886238 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9427. Min Range: -3.9427
Max Act: 3.8176. Min Act: -0.1700
Data Index: 4944827 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9427. Min Range: -3.9427
Max Act: 3.8176. Min Act: -0.1700
Data Index: 2704468 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9427. Min Range: -3.9427
Max Act: 3.8176. Min Act: -0.1700
Data Index: 5103265 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9427. Min Range: -3.9427
Max Act: 3.8176. Min Act: -0.1700
Data Index: 5919871 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9427. Min Range: -3.9427
Max Act: 3.8176. Min Act: -0.1700
Data Index: 1285732 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19