Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3201 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1661. Min Range: -7.1661
Max Act: 7.1661. Min Act: -0.1700
Data Index: 178551 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1661. Min Range: -7.1661
Max Act: 6.9786. Min Act: -0.1700
Data Index: 1822398 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1661. Min Range: -7.1661
Max Act: 6.9161. Min Act: -0.1700
Data Index: 5651232 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1661. Min Range: -7.1661
Max Act: 6.9161. Min Act: -0.1700
Data Index: 5896796 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1661. Min Range: -7.1661
Max Act: 6.8849. Min Act: -0.1700
Data Index: 6317820 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1661. Min Range: -7.1661
Max Act: 6.7911. Min Act: -0.1700
Data Index: 4736392 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1661. Min Range: -7.1661
Max Act: 6.7286. Min Act: -0.1700
Data Index: 8083214 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1661. Min Range: -7.1661
Max Act: 6.7286. Min Act: -0.1700
Data Index: 1015971 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1661. Min Range: -7.1661
Max Act: 6.7286. Min Act: -0.1700
Data Index: 8567071 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1661. Min Range: -7.1661
Max Act: 6.7286. Min Act: -0.1700
Data Index: 8366427 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1661. Min Range: -7.1661
Max Act: 6.6661. Min Act: -0.1700
Data Index: 8030148 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1661. Min Range: -7.1661
Max Act: 6.6036. Min Act: -0.1700
Data Index: 3005057 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1661. Min Range: -7.1661
Max Act: 6.6349. Min Act: -0.1700
Data Index: 8169332 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1661. Min Range: -7.1661
Max Act: 6.5724. Min Act: -0.1700
Data Index: 3603031 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1661. Min Range: -7.1661
Max Act: 6.5724. Min Act: -0.1700
Data Index: 356021 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1661. Min Range: -7.1661
Max Act: 6.5411. Min Act: -0.1700
Data Index: 8353164 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1661. Min Range: -7.1661
Max Act: 6.5411. Min Act: -0.1700
Data Index: 3840290 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1661. Min Range: -7.1661
Max Act: 6.5411. Min Act: -0.1700
Data Index: 4404130 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1661. Min Range: -7.1661
Max Act: 6.5411. Min Act: -0.1700
Data Index: 3168620 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1661. Min Range: -7.1661
Max Act: 6.4786. Min Act: -0.1700
Data Index: 2595263 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19