Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5821 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5788. Min Range: -3.5788
Max Act: 3.5788. Min Act: -0.1700
Data Index: 1617212 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5788. Min Range: -3.5788
Max Act: 3.5475. Min Act: -0.1700
Data Index: 156291 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5788. Min Range: -3.5788
Max Act: 3.5161. Min Act: -0.1700
Data Index: 8408618 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5788. Min Range: -3.5788
Max Act: 3.5161. Min Act: -0.1700
Data Index: 7443758 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5788. Min Range: -3.5788
Max Act: 3.5161. Min Act: -0.1700
Data Index: 4047507 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5788. Min Range: -3.5788
Max Act: 3.5161. Min Act: -0.1700
Data Index: 2277400 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5788. Min Range: -3.5788
Max Act: 3.4848. Min Act: -0.1700
Data Index: 379445 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5788. Min Range: -3.5788
Max Act: 3.4848. Min Act: -0.1700
Data Index: 6137818 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5788. Min Range: -3.5788
Max Act: 3.4535. Min Act: -0.1700
Data Index: 5560519 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5788. Min Range: -3.5788
Max Act: 3.4535. Min Act: -0.1700
Data Index: 5577819 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5788. Min Range: -3.5788
Max Act: 3.4535. Min Act: -0.1700
Data Index: 6137825 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5788. Min Range: -3.5788
Max Act: 3.4535. Min Act: -0.1700
Data Index: 4456755 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5788. Min Range: -3.5788
Max Act: 3.4221. Min Act: -0.1700
Data Index: 156293 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5788. Min Range: -3.5788
Max Act: 3.4221. Min Act: -0.1700
Data Index: 4092072 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5788. Min Range: -3.5788
Max Act: 3.4221. Min Act: -0.1700
Data Index: 2403390 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5788. Min Range: -3.5788
Max Act: 3.4535. Min Act: -0.1700
Data Index: 646252 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5788. Min Range: -3.5788
Max Act: 3.4221. Min Act: -0.1700
Data Index: 7517010 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5788. Min Range: -3.5788
Max Act: 3.4221. Min Act: -0.1700
Data Index: 7345028 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5788. Min Range: -3.5788
Max Act: 3.4221. Min Act: -0.1700
Data Index: 7187870 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5788. Min Range: -3.5788
Max Act: 3.4221. Min Act: -0.1700
Data Index: 6968787 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19