Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3021 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.2290. Min Act: -0.1700
Data Index: 5310226 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.2290. Min Act: -0.1700
Data Index: 8811360 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.1665. Min Act: -0.1700
Data Index: 8186875 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.1665. Min Act: -0.1700
Data Index: 1636950 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.1352. Min Act: -0.1700
Data Index: 3753576 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.1352. Min Act: -0.1700
Data Index: 7494254 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.1040. Min Act: -0.1700
Data Index: 7349388 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.1352. Min Act: -0.1700
Data Index: 6297055 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.1352. Min Act: -0.1700
Data Index: 4662000 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.1665. Min Act: -0.1700
Data Index: 4544999 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.1040. Min Act: -0.1700
Data Index: 420530 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.1040. Min Act: -0.1700
Data Index: 5879538 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.1040. Min Act: -0.1700
Data Index: 8218351 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.1040. Min Act: -0.1700
Data Index: 4156417 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.1040. Min Act: -0.1700
Data Index: 4332977 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.1040. Min Act: -0.1700
Data Index: 4575944 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.0727. Min Act: -0.1700
Data Index: 8218355 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.0727. Min Act: -0.1700
Data Index: 4859954 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.0727. Min Act: -0.1700
Data Index: 3636523 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2290. Min Range: -5.2290
Max Act: 5.0727. Min Act: -0.1700
Data Index: 7077060 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19