Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4204 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8514. Min Range: -6.8514
Max Act: 6.8514. Min Act: -0.1700
Data Index: 257028 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8514. Min Range: -6.8514
Max Act: 6.5389. Min Act: -0.1700
Data Index: 3830236 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8514. Min Range: -6.8514
Max Act: 6.3827. Min Act: -0.1700
Data Index: 1943942 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8514. Min Range: -6.8514
Max Act: 6.3827. Min Act: -0.1700
Data Index: 2388557 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8514. Min Range: -6.8514
Max Act: 6.3514. Min Act: -0.1700
Data Index: 4850785 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8514. Min Range: -6.8514
Max Act: 6.2889. Min Act: -0.1700
Data Index: 6898991 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8514. Min Range: -6.8514
Max Act: 6.2264. Min Act: -0.1700
Data Index: 5011058 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8514. Min Range: -6.8514
Max Act: 6.1952. Min Act: -0.1700
Data Index: 2852602 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8514. Min Range: -6.8514
Max Act: 6.1639. Min Act: -0.1700
Data Index: 1705545 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8514. Min Range: -6.8514
Max Act: 6.1639. Min Act: -0.1700
Data Index: 1378307 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8514. Min Range: -6.8514
Max Act: 6.1327. Min Act: -0.1700
Data Index: 5933756 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8514. Min Range: -6.8514
Max Act: 6.1327. Min Act: -0.1700
Data Index: 5916882 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8514. Min Range: -6.8514
Max Act: 6.1014. Min Act: -0.1700
Data Index: 5553066 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8514. Min Range: -6.8514
Max Act: 6.0389. Min Act: -0.1700
Data Index: 3500480 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8514. Min Range: -6.8514
Max Act: 6.0389. Min Act: -0.1700
Data Index: 185186 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8514. Min Range: -6.8514
Max Act: 6.0077. Min Act: -0.1700
Data Index: 1970270 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8514. Min Range: -6.8514
Max Act: 6.0077. Min Act: -0.1700
Data Index: 1315243 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8514. Min Range: -6.8514
Max Act: 6.0077. Min Act: -0.1700
Data Index: 2145535 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8514. Min Range: -6.8514
Max Act: 5.9764. Min Act: -0.1700
Data Index: 3167242 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8514. Min Range: -6.8514
Max Act: 5.9764. Min Act: -0.1700
Data Index: 2174614 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19