Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2731 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5530. Min Range: -1.5530
Max Act: 1.5530. Min Act: -0.1698
Data Index: 4119133 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5530. Min Range: -1.5530
Max Act: 1.5442. Min Act: -0.1697
Data Index: 2876150 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5530. Min Range: -1.5530
Max Act: 1.5267. Min Act: -0.1690
Data Index: 4972817 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5530. Min Range: -1.5530
Max Act: 1.5179. Min Act: -0.1700
Data Index: 6778203 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5530. Min Range: -1.5530
Max Act: 1.5267. Min Act: -0.1698
Data Index: 337817 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5530. Min Range: -1.5530
Max Act: 1.5179. Min Act: -0.1699
Data Index: 245464 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5530. Min Range: -1.5530
Max Act: 1.5179. Min Act: -0.1700
Data Index: 5219123 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5530. Min Range: -1.5530
Max Act: 1.5092. Min Act: -0.1700
Data Index: 1684613 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5530. Min Range: -1.5530
Max Act: 1.5004. Min Act: -0.1700
Data Index: 5030094 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5530. Min Range: -1.5530
Max Act: 1.5004. Min Act: -0.1700
Data Index: 8152823 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5530. Min Range: -1.5530
Max Act: 1.4916. Min Act: -0.1700
Data Index: 3464593 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5530. Min Range: -1.5530
Max Act: 1.4916. Min Act: -0.1700
Data Index: 5581780 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5530. Min Range: -1.5530
Max Act: 1.5004. Min Act: -0.1700
Data Index: 8148958 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5530. Min Range: -1.5530
Max Act: 1.5004. Min Act: -0.1699
Data Index: 595003 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5530. Min Range: -1.5530
Max Act: 1.5092. Min Act: -0.1700
Data Index: 5674818 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5530. Min Range: -1.5530
Max Act: 1.4916. Min Act: -0.1700
Data Index: 5392650 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5530. Min Range: -1.5530
Max Act: 1.4916. Min Act: -0.1700
Data Index: 2636031 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5530. Min Range: -1.5530
Max Act: 1.4828. Min Act: -0.1700
Data Index: 5674300 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5530. Min Range: -1.5530
Max Act: 1.4916. Min Act: -0.1700
Data Index: 10716 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5530. Min Range: -1.5530
Max Act: 1.4828. Min Act: -0.1700
Data Index: 2866399 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19