Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 392 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6946. Min Range: -7.6946
Max Act: 7.6946. Min Act: -0.1700
Data Index: 7831890 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6946. Min Range: -7.6946
Max Act: 7.6009. Min Act: -0.1700
Data Index: 5078754 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6946. Min Range: -7.6946
Max Act: 7.5071. Min Act: -0.1700
Data Index: 3733019 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6946. Min Range: -7.6946
Max Act: 7.5071. Min Act: -0.1700
Data Index: 435055 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6946. Min Range: -7.6946
Max Act: 7.4134. Min Act: -0.1700
Data Index: 328752 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6946. Min Range: -7.6946
Max Act: 7.3821. Min Act: -0.1700
Data Index: 5677963 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6946. Min Range: -7.6946
Max Act: 7.3821. Min Act: -0.1700
Data Index: 1947075 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6946. Min Range: -7.6946
Max Act: 7.2884. Min Act: -0.1700
Data Index: 1626397 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6946. Min Range: -7.6946
Max Act: 7.3196. Min Act: -0.1700
Data Index: 1261116 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6946. Min Range: -7.6946
Max Act: 7.3509. Min Act: -0.1700
Data Index: 2926179 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6946. Min Range: -7.6946
Max Act: 7.2884. Min Act: -0.1700
Data Index: 4653085 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6946. Min Range: -7.6946
Max Act: 7.2571. Min Act: -0.1700
Data Index: 1461465 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6946. Min Range: -7.6946
Max Act: 7.2571. Min Act: -0.1700
Data Index: 909483 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6946. Min Range: -7.6946
Max Act: 7.2884. Min Act: -0.1700
Data Index: 6332951 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6946. Min Range: -7.6946
Max Act: 7.1946. Min Act: -0.1700
Data Index: 2858266 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6946. Min Range: -7.6946
Max Act: 7.2571. Min Act: -0.1700
Data Index: 1099427 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6946. Min Range: -7.6946
Max Act: 7.2259. Min Act: -0.1700
Data Index: 2219136 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6946. Min Range: -7.6946
Max Act: 7.2571. Min Act: -0.1700
Data Index: 4263506 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6946. Min Range: -7.6946
Max Act: 7.2259. Min Act: -0.1700
Data Index: 4457212 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6946. Min Range: -7.6946
Max Act: 7.1946. Min Act: -0.1700
Data Index: 3452178 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19