Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1804 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4847. Min Range: -3.4847
Max Act: 3.4847. Min Act: -0.1700
Data Index: 1360882 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4847. Min Range: -3.4847
Max Act: 3.3750. Min Act: -0.1700
Data Index: 589425 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4847. Min Range: -3.4847
Max Act: 3.3593. Min Act: -0.1700
Data Index: 4945235 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4847. Min Range: -3.4847
Max Act: 3.3122. Min Act: -0.1700
Data Index: 1360883 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4847. Min Range: -3.4847
Max Act: 3.2965. Min Act: -0.1700
Data Index: 691003 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4847. Min Range: -3.4847
Max Act: 3.2651. Min Act: -0.1700
Data Index: 1015485 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4847. Min Range: -3.4847
Max Act: 3.2965. Min Act: -0.1700
Data Index: 1434127 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4847. Min Range: -3.4847
Max Act: 3.2494. Min Act: -0.1700
Data Index: 2101405 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4847. Min Range: -3.4847
Max Act: 3.2651. Min Act: -0.1700
Data Index: 1108266 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4847. Min Range: -3.4847
Max Act: 3.2651. Min Act: -0.1700
Data Index: 1827637 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4847. Min Range: -3.4847
Max Act: 3.2651. Min Act: -0.1700
Data Index: 5570244 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4847. Min Range: -3.4847
Max Act: 3.2494. Min Act: -0.1700
Data Index: 114001 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4847. Min Range: -3.4847
Max Act: 3.2337. Min Act: -0.1700
Data Index: 3387783 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4847. Min Range: -3.4847
Max Act: 3.2337. Min Act: -0.1700
Data Index: 5507943 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4847. Min Range: -3.4847
Max Act: 3.2179. Min Act: -0.1700
Data Index: 972123 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4847. Min Range: -3.4847
Max Act: 3.2179. Min Act: -0.1700
Data Index: 1192416 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4847. Min Range: -3.4847
Max Act: 3.2179. Min Act: -0.1700
Data Index: 160949 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4847. Min Range: -3.4847
Max Act: 3.1865. Min Act: -0.1700
Data Index: 4015180 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4847. Min Range: -3.4847
Max Act: 3.2022. Min Act: -0.1700
Data Index: 2201036 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4847. Min Range: -3.4847
Max Act: 3.2022. Min Act: -0.1700
Data Index: 1418026 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19