Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4829 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6731. Min Range: -4.6731
Max Act: 4.6731. Min Act: -0.1700
Data Index: 4824809 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6731. Min Range: -4.6731
Max Act: 4.5793. Min Act: -0.1700
Data Index: 957857 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6731. Min Range: -4.6731
Max Act: 4.5481. Min Act: -0.1700
Data Index: 1348847 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6731. Min Range: -4.6731
Max Act: 4.4543. Min Act: -0.1700
Data Index: 5193950 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6731. Min Range: -4.6731
Max Act: 4.4231. Min Act: -0.1700
Data Index: 596288 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6731. Min Range: -4.6731
Max Act: 4.3918. Min Act: -0.1700
Data Index: 3303644 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6731. Min Range: -4.6731
Max Act: 4.3605. Min Act: -0.1700
Data Index: 6853267 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6731. Min Range: -4.6731
Max Act: 4.2980. Min Act: -0.1700
Data Index: 5299215 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6731. Min Range: -4.6731
Max Act: 4.3293. Min Act: -0.1700
Data Index: 7975173 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6731. Min Range: -4.6731
Max Act: 4.3293. Min Act: -0.1700
Data Index: 6254001 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6731. Min Range: -4.6731
Max Act: 4.3293. Min Act: -0.1700
Data Index: 6426284 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6731. Min Range: -4.6731
Max Act: 4.2980. Min Act: -0.1700
Data Index: 7699321 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6731. Min Range: -4.6731
Max Act: 4.2980. Min Act: -0.1700
Data Index: 4364582 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6731. Min Range: -4.6731
Max Act: 4.2980. Min Act: -0.1700
Data Index: 8723180 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6731. Min Range: -4.6731
Max Act: 4.2980. Min Act: -0.1700
Data Index: 2618478 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6731. Min Range: -4.6731
Max Act: 4.2668. Min Act: -0.1700
Data Index: 8266609 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6731. Min Range: -4.6731
Max Act: 4.2668. Min Act: -0.1700
Data Index: 3422992 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6731. Min Range: -4.6731
Max Act: 4.2668. Min Act: -0.1700
Data Index: 2213735 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6731. Min Range: -4.6731
Max Act: 4.2668. Min Act: -0.1700
Data Index: 3095412 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6731. Min Range: -4.6731
Max Act: 4.2355. Min Act: -0.1700
Data Index: 1706116 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19