Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2599 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.6040. Min Act: -0.1700
Data Index: 2376985 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.5414. Min Act: -0.1700
Data Index: 5735889 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.4788. Min Act: -0.1700
Data Index: 2740304 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.4788. Min Act: -0.1700
Data Index: 7689588 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.4788. Min Act: -0.1700
Data Index: 123685 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.4474. Min Act: -0.1700
Data Index: 1042509 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.4161. Min Act: -0.1700
Data Index: 6569678 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.4161. Min Act: -0.1700
Data Index: 7381577 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.4161. Min Act: -0.1700
Data Index: 1674278 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.4161. Min Act: -0.1700
Data Index: 3378050 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.4161. Min Act: -0.1700
Data Index: 6488998 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.4161. Min Act: -0.1700
Data Index: 8070389 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.3847. Min Act: -0.1700
Data Index: 3568561 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.3377. Min Act: -0.1700
Data Index: 87736 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.3690. Min Act: -0.1700
Data Index: 84245 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.3690. Min Act: -0.1700
Data Index: 6903750 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.3690. Min Act: -0.1700
Data Index: 619672 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.4004. Min Act: -0.1700
Data Index: 5413717 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.4004. Min Act: -0.1700
Data Index: 6307811 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6040. Min Range: -3.6040
Max Act: 3.2906. Min Act: -0.1700
Data Index: 4448800 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19