Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 619 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8232. Min Range: -3.8232
Max Act: 3.8232. Min Act: -0.1700
Data Index: 5974025 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8232. Min Range: -3.8232
Max Act: 3.7919. Min Act: -0.1700
Data Index: 1564568 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8232. Min Range: -3.8232
Max Act: 3.7450. Min Act: -0.1700
Data Index: 517496 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8232. Min Range: -3.8232
Max Act: 3.7294. Min Act: -0.1700
Data Index: 7491309 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8232. Min Range: -3.8232
Max Act: 3.6824. Min Act: -0.1700
Data Index: 3092081 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8232. Min Range: -3.8232
Max Act: 3.6668. Min Act: -0.1700
Data Index: 6550137 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8232. Min Range: -3.8232
Max Act: 3.6668. Min Act: -0.1700
Data Index: 1054751 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8232. Min Range: -3.8232
Max Act: 3.6668. Min Act: -0.1700
Data Index: 7524358 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8232. Min Range: -3.8232
Max Act: 3.6198. Min Act: -0.1700
Data Index: 7598640 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8232. Min Range: -3.8232
Max Act: 3.5729. Min Act: -0.1700
Data Index: 7660995 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8232. Min Range: -3.8232
Max Act: 3.5259. Min Act: -0.1700
Data Index: 517500 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8232. Min Range: -3.8232
Max Act: 3.5259. Min Act: -0.1700
Data Index: 4601067 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8232. Min Range: -3.8232
Max Act: 3.5416. Min Act: -0.1700
Data Index: 4638499 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8232. Min Range: -3.8232
Max Act: 3.5103. Min Act: -0.1700
Data Index: 1735269 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8232. Min Range: -3.8232
Max Act: 3.5416. Min Act: -0.1700
Data Index: 2024042 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8232. Min Range: -3.8232
Max Act: 3.5103. Min Act: -0.1700
Data Index: 8062549 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8232. Min Range: -3.8232
Max Act: 3.4946. Min Act: -0.1700
Data Index: 2816039 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8232. Min Range: -3.8232
Max Act: 3.4946. Min Act: -0.1700
Data Index: 3917328 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8232. Min Range: -3.8232
Max Act: 3.4946. Min Act: -0.1700
Data Index: 451156 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8232. Min Range: -3.8232
Max Act: 3.4633. Min Act: -0.1700
Data Index: 5962856 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19