Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1895 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6254. Min Range: -4.6254
Max Act: 4.6254. Min Act: -0.1700
Data Index: 5847650 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6254. Min Range: -4.6254
Max Act: 4.6254. Min Act: -0.1700
Data Index: 44854 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6254. Min Range: -4.6254
Max Act: 4.6254. Min Act: -0.1700
Data Index: 56837 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6254. Min Range: -4.6254
Max Act: 4.5941. Min Act: -0.1700
Data Index: 2841597 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6254. Min Range: -4.6254
Max Act: 4.5941. Min Act: -0.1700
Data Index: 4507819 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6254. Min Range: -4.6254
Max Act: 4.5629. Min Act: -0.1700
Data Index: 6248745 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6254. Min Range: -4.6254
Max Act: 4.5316. Min Act: -0.1700
Data Index: 3304267 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6254. Min Range: -4.6254
Max Act: 4.5004. Min Act: -0.1700
Data Index: 5878431 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6254. Min Range: -4.6254
Max Act: 4.4691. Min Act: -0.1700
Data Index: 8786027 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6254. Min Range: -4.6254
Max Act: 4.4691. Min Act: -0.1700
Data Index: 1242819 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6254. Min Range: -4.6254
Max Act: 4.4691. Min Act: -0.1700
Data Index: 1754607 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6254. Min Range: -4.6254
Max Act: 4.4691. Min Act: -0.1700
Data Index: 6247406 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6254. Min Range: -4.6254
Max Act: 4.4691. Min Act: -0.1700
Data Index: 3844066 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6254. Min Range: -4.6254
Max Act: 4.4691. Min Act: -0.1700
Data Index: 7493505 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6254. Min Range: -4.6254
Max Act: 4.4379. Min Act: -0.1700
Data Index: 1707800 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6254. Min Range: -4.6254
Max Act: 4.4379. Min Act: -0.1700
Data Index: 2360235 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6254. Min Range: -4.6254
Max Act: 4.4379. Min Act: -0.1700
Data Index: 3955219 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6254. Min Range: -4.6254
Max Act: 4.4379. Min Act: -0.1700
Data Index: 7244999 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6254. Min Range: -4.6254
Max Act: 4.4379. Min Act: -0.1700
Data Index: 6235795 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6254. Min Range: -4.6254
Max Act: 4.4066. Min Act: -0.1700
Data Index: 5154795 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19