Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2064 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4573. Min Range: -6.4573
Max Act: 6.4573. Min Act: -0.1700
Data Index: 3813744 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4573. Min Range: -6.4573
Max Act: 6.3948. Min Act: -0.1700
Data Index: 353190 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4573. Min Range: -6.4573
Max Act: 6.3010. Min Act: -0.1700
Data Index: 1598206 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4573. Min Range: -6.4573
Max Act: 6.2698. Min Act: -0.1700
Data Index: 1036023 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4573. Min Range: -6.4573
Max Act: 6.3323. Min Act: -0.1700
Data Index: 3264222 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4573. Min Range: -6.4573
Max Act: 6.2385. Min Act: -0.1700
Data Index: 8175258 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4573. Min Range: -6.4573
Max Act: 6.2385. Min Act: -0.1700
Data Index: 7891674 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4573. Min Range: -6.4573
Max Act: 6.2073. Min Act: -0.1700
Data Index: 2385362 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4573. Min Range: -6.4573
Max Act: 6.2385. Min Act: -0.1700
Data Index: 2130670 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4573. Min Range: -6.4573
Max Act: 6.2073. Min Act: -0.1700
Data Index: 4030647 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4573. Min Range: -6.4573
Max Act: 6.2073. Min Act: -0.1700
Data Index: 5852095 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4573. Min Range: -6.4573
Max Act: 6.1760. Min Act: -0.1700
Data Index: 1524864 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4573. Min Range: -6.4573
Max Act: 6.1448. Min Act: -0.1700
Data Index: 5144737 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4573. Min Range: -6.4573
Max Act: 6.1135. Min Act: -0.1700
Data Index: 4940587 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4573. Min Range: -6.4573
Max Act: 6.1448. Min Act: -0.1700
Data Index: 6240342 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4573. Min Range: -6.4573
Max Act: 6.1448. Min Act: -0.1700
Data Index: 2684280 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4573. Min Range: -6.4573
Max Act: 6.0823. Min Act: -0.1700
Data Index: 2671350 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4573. Min Range: -6.4573
Max Act: 6.1135. Min Act: -0.1700
Data Index: 184263 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4573. Min Range: -6.4573
Max Act: 6.1135. Min Act: -0.1700
Data Index: 4872963 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4573. Min Range: -6.4573
Max Act: 6.0823. Min Act: -0.1700
Data Index: 6605100 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19