Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1382 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4179. Min Range: -4.4179
Max Act: 4.4179. Min Act: -0.1700
Data Index: 1845171 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4179. Min Range: -4.4179
Max Act: 4.2616. Min Act: -0.1700
Data Index: 2795773 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4179. Min Range: -4.4179
Max Act: 4.2929. Min Act: -0.1700
Data Index: 4296094 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4179. Min Range: -4.4179
Max Act: 4.2616. Min Act: -0.1700
Data Index: 3770325 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4179. Min Range: -4.4179
Max Act: 4.2304. Min Act: -0.1700
Data Index: 1903269 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4179. Min Range: -4.4179
Max Act: 4.2304. Min Act: -0.1700
Data Index: 5071954 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4179. Min Range: -4.4179
Max Act: 4.2304. Min Act: -0.1700
Data Index: 4105320 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4179. Min Range: -4.4179
Max Act: 4.2304. Min Act: -0.1700
Data Index: 3422713 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4179. Min Range: -4.4179
Max Act: 4.1991. Min Act: -0.1699
Data Index: 5476873 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4179. Min Range: -4.4179
Max Act: 4.1366. Min Act: -0.1700
Data Index: 3706596 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4179. Min Range: -4.4179
Max Act: 4.1679. Min Act: -0.1700
Data Index: 1488407 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4179. Min Range: -4.4179
Max Act: 4.1679. Min Act: -0.1700
Data Index: 7084898 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4179. Min Range: -4.4179
Max Act: 4.1679. Min Act: -0.1700
Data Index: 7556548 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4179. Min Range: -4.4179
Max Act: 4.1679. Min Act: -0.1700
Data Index: 8786167 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4179. Min Range: -4.4179
Max Act: 4.1366. Min Act: -0.1700
Data Index: 3029813 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4179. Min Range: -4.4179
Max Act: 4.1366. Min Act: -0.1700
Data Index: 3706600 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4179. Min Range: -4.4179
Max Act: 4.1366. Min Act: -0.1700
Data Index: 155524 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4179. Min Range: -4.4179
Max Act: 4.1366. Min Act: -0.1700
Data Index: 7140602 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4179. Min Range: -4.4179
Max Act: 4.1366. Min Act: -0.1700
Data Index: 267169 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4179. Min Range: -4.4179
Max Act: 4.1366. Min Act: -0.1700
Data Index: 1109050 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19