Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2139 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1168. Min Range: -6.1168
Max Act: 6.1168. Min Act: -0.1700
Data Index: 8413156 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1168. Min Range: -6.1168
Max Act: 5.8668. Min Act: -0.1700
Data Index: 597716 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1168. Min Range: -6.1168
Max Act: 5.8355. Min Act: -0.1700
Data Index: 1413164 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1168. Min Range: -6.1168
Max Act: 5.8668. Min Act: -0.1700
Data Index: 3596838 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1168. Min Range: -6.1168
Max Act: 5.8355. Min Act: -0.1700
Data Index: 3224945 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1168. Min Range: -6.1168
Max Act: 5.8355. Min Act: -0.1700
Data Index: 6075481 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1168. Min Range: -6.1168
Max Act: 5.8043. Min Act: -0.1700
Data Index: 110249 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1168. Min Range: -6.1168
Max Act: 5.8043. Min Act: -0.1700
Data Index: 4016767 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1168. Min Range: -6.1168
Max Act: 5.7418. Min Act: -0.1700
Data Index: 2623572 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1168. Min Range: -6.1168
Max Act: 5.7730. Min Act: -0.1700
Data Index: 7360107 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1168. Min Range: -6.1168
Max Act: 5.7730. Min Act: -0.1700
Data Index: 1269116 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1168. Min Range: -6.1168
Max Act: 5.8043. Min Act: -0.1700
Data Index: 2131304 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1168. Min Range: -6.1168
Max Act: 5.7730. Min Act: -0.1700
Data Index: 4240976 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1168. Min Range: -6.1168
Max Act: 5.7418. Min Act: -0.1700
Data Index: 1936844 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1168. Min Range: -6.1168
Max Act: 5.7418. Min Act: -0.1700
Data Index: 988321 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1168. Min Range: -6.1168
Max Act: 5.7418. Min Act: -0.1700
Data Index: 1413956 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1168. Min Range: -6.1168
Max Act: 5.7418. Min Act: -0.1700
Data Index: 5910525 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1168. Min Range: -6.1168
Max Act: 5.6793. Min Act: -0.1700
Data Index: 1913551 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1168. Min Range: -6.1168
Max Act: 5.7105. Min Act: -0.1700
Data Index: 215754 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1168. Min Range: -6.1168
Max Act: 5.7105. Min Act: -0.1700
Data Index: 28477 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19