Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3927 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4462. Min Range: -6.4462
Max Act: 6.4462. Min Act: -0.1700
Data Index: 8184920 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4462. Min Range: -6.4462
Max Act: 6.4462. Min Act: -0.1700
Data Index: 8745303 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4462. Min Range: -6.4462
Max Act: 6.3837. Min Act: -0.1700
Data Index: 5828089 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4462. Min Range: -6.4462
Max Act: 6.3524. Min Act: -0.1700
Data Index: 4460410 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4462. Min Range: -6.4462
Max Act: 6.3212. Min Act: -0.1700
Data Index: 4794874 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4462. Min Range: -6.4462
Max Act: 6.3212. Min Act: -0.1700
Data Index: 7750588 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4462. Min Range: -6.4462
Max Act: 6.2587. Min Act: -0.1700
Data Index: 7145306 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4462. Min Range: -6.4462
Max Act: 6.2274. Min Act: -0.1700
Data Index: 436636 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4462. Min Range: -6.4462
Max Act: 6.2274. Min Act: -0.1700
Data Index: 4224591 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4462. Min Range: -6.4462
Max Act: 6.2274. Min Act: -0.1700
Data Index: 5984369 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4462. Min Range: -6.4462
Max Act: 6.2274. Min Act: -0.1700
Data Index: 1186101 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4462. Min Range: -6.4462
Max Act: 6.1962. Min Act: -0.1700
Data Index: 2553014 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4462. Min Range: -6.4462
Max Act: 6.1962. Min Act: -0.1700
Data Index: 1991009 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4462. Min Range: -6.4462
Max Act: 6.1649. Min Act: -0.1700
Data Index: 8807186 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4462. Min Range: -6.4462
Max Act: 6.1337. Min Act: -0.1700
Data Index: 6581114 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4462. Min Range: -6.4462
Max Act: 6.1649. Min Act: -0.1700
Data Index: 33879 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4462. Min Range: -6.4462
Max Act: 6.1337. Min Act: -0.1700
Data Index: 7777475 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4462. Min Range: -6.4462
Max Act: 6.1962. Min Act: -0.1700
Data Index: 2098241 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4462. Min Range: -6.4462
Max Act: 6.1649. Min Act: -0.1700
Data Index: 6838294 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4462. Min Range: -6.4462
Max Act: 6.1337. Min Act: -0.1700
Data Index: 4765026 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19