Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2996 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4235. Min Range: -4.4235
Max Act: 4.4235. Min Act: -0.1700
Data Index: 6073019 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4235. Min Range: -4.4235
Max Act: 4.3610. Min Act: -0.1700
Data Index: 2407702 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4235. Min Range: -4.4235
Max Act: 4.2048. Min Act: -0.1700
Data Index: 4100059 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4235. Min Range: -4.4235
Max Act: 4.2048. Min Act: -0.1700
Data Index: 4599994 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4235. Min Range: -4.4235
Max Act: 4.1735. Min Act: -0.1700
Data Index: 7127830 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4235. Min Range: -4.4235
Max Act: 4.1110. Min Act: -0.1700
Data Index: 7815751 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4235. Min Range: -4.4235
Max Act: 4.0798. Min Act: -0.1700
Data Index: 5575541 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4235. Min Range: -4.4235
Max Act: 4.0798. Min Act: -0.1700
Data Index: 4872300 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4235. Min Range: -4.4235
Max Act: 4.0485. Min Act: -0.1700
Data Index: 1535526 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4235. Min Range: -4.4235
Max Act: 4.0485. Min Act: -0.1700
Data Index: 4429213 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4235. Min Range: -4.4235
Max Act: 4.0485. Min Act: -0.1700
Data Index: 6305441 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4235. Min Range: -4.4235
Max Act: 4.0172. Min Act: -0.1700
Data Index: 4444462 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4235. Min Range: -4.4235
Max Act: 4.0172. Min Act: -0.1700
Data Index: 7535549 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4235. Min Range: -4.4235
Max Act: 4.0172. Min Act: -0.1700
Data Index: 8549974 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4235. Min Range: -4.4235
Max Act: 4.0172. Min Act: -0.1700
Data Index: 4336671 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.9860. Min Act: -0.1700
Data Index: 6974770 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.9547. Min Act: -0.1700
Data Index: 8092490 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.9860. Min Act: -0.1700
Data Index: 3137916 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.9547. Min Act: -0.1700
Data Index: 974589 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4235. Min Range: -4.4235
Max Act: 3.9860. Min Act: -0.1700
Data Index: 4398520 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19