Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3554 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.8337. Min Act: -0.1700
Data Index: 3788235 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.6149. Min Act: -0.1700
Data Index: 4950563 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.6462. Min Act: -0.1700
Data Index: 2297733 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.5524. Min Act: -0.1700
Data Index: 5333072 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.5212. Min Act: -0.1700
Data Index: 3339226 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.4899. Min Act: -0.1700
Data Index: 1404393 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.4274. Min Act: -0.1700
Data Index: 7289287 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.4274. Min Act: -0.1700
Data Index: 5156334 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.3649. Min Act: -0.1700
Data Index: 553531 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.3649. Min Act: -0.1700
Data Index: 5134797 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.3649. Min Act: -0.1700
Data Index: 1023742 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.3649. Min Act: -0.1700
Data Index: 8226653 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.3649. Min Act: -0.1700
Data Index: 3494338 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.3336. Min Act: -0.1700
Data Index: 5579744 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.3024. Min Act: -0.1700
Data Index: 2144463 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.2711. Min Act: -0.1700
Data Index: 6327673 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.3024. Min Act: -0.1700
Data Index: 8390690 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.3024. Min Act: -0.1700
Data Index: 2512370 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.2711. Min Act: -0.1700
Data Index: 3809778 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8337. Min Range: -4.8337
Max Act: 4.2711. Min Act: -0.1700
Data Index: 3979830 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19