Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2730 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8348. Min Range: -6.8348
Max Act: 6.8348. Min Act: -0.1700
Data Index: 7305484 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8348. Min Range: -6.8348
Max Act: 6.7410. Min Act: -0.1700
Data Index: 8370750 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8348. Min Range: -6.8348
Max Act: 6.7098. Min Act: -0.1700
Data Index: 466237 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8348. Min Range: -6.8348
Max Act: 6.6785. Min Act: -0.1700
Data Index: 7048964 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8348. Min Range: -6.8348
Max Act: 6.7410. Min Act: -0.1700
Data Index: 6806825 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8348. Min Range: -6.8348
Max Act: 6.5848. Min Act: -0.1700
Data Index: 5437183 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8348. Min Range: -6.8348
Max Act: 6.5535. Min Act: -0.1700
Data Index: 5911073 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8348. Min Range: -6.8348
Max Act: 6.5223. Min Act: -0.1700
Data Index: 8682748 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8348. Min Range: -6.8348
Max Act: 6.5223. Min Act: -0.1700
Data Index: 4951726 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8348. Min Range: -6.8348
Max Act: 6.4910. Min Act: -0.1700
Data Index: 6370413 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8348. Min Range: -6.8348
Max Act: 6.4598. Min Act: -0.1700
Data Index: 122750 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8348. Min Range: -6.8348
Max Act: 6.3660. Min Act: -0.1700
Data Index: 3060959 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8348. Min Range: -6.8348
Max Act: 6.3973. Min Act: -0.1700
Data Index: 5720997 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8348. Min Range: -6.8348
Max Act: 6.3973. Min Act: -0.1700
Data Index: 5544730 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8348. Min Range: -6.8348
Max Act: 6.3348. Min Act: -0.1700
Data Index: 1220699 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8348. Min Range: -6.8348
Max Act: 6.3348. Min Act: -0.1700
Data Index: 4772643 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8348. Min Range: -6.8348
Max Act: 6.3348. Min Act: -0.1700
Data Index: 675465 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8348. Min Range: -6.8348
Max Act: 6.3348. Min Act: -0.1700
Data Index: 3700481 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8348. Min Range: -6.8348
Max Act: 6.3035. Min Act: -0.1700
Data Index: 1956992 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8348. Min Range: -6.8348
Max Act: 6.3035. Min Act: -0.1700
Data Index: 1960655 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19