Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3933 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.7868. Min Act: -0.1700
Data Index: 5494150 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.7555. Min Act: -0.1700
Data Index: 805949 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.7243. Min Act: -0.1700
Data Index: 5368434 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.6930. Min Act: -0.1700
Data Index: 7889987 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.6930. Min Act: -0.1700
Data Index: 6676790 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.6305. Min Act: -0.1700
Data Index: 764913 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5680. Min Act: -0.1700
Data Index: 1815027 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5368. Min Act: -0.1700
Data Index: 7799441 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5368. Min Act: -0.1700
Data Index: 8429097 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5055. Min Act: -0.1700
Data Index: 805950 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5055. Min Act: -0.1700
Data Index: 5254407 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5055. Min Act: -0.1700
Data Index: 1600674 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5055. Min Act: -0.1700
Data Index: 8016112 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5055. Min Act: -0.1700
Data Index: 3993937 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5055. Min Act: -0.1700
Data Index: 4135671 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.4743. Min Act: -0.1700
Data Index: 3167019 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.4743. Min Act: -0.1700
Data Index: 1769135 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.4743. Min Act: -0.1700
Data Index: 4775281 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.5055. Min Act: -0.1700
Data Index: 7783430 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7868. Min Range: -4.7868
Max Act: 4.4743. Min Act: -0.1700
Data Index: 7155635 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19