Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6008 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8543. Min Range: -3.8543
Max Act: 3.8543. Min Act: -0.1700
Data Index: 8245158 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8543. Min Range: -3.8543
Max Act: 3.8230. Min Act: -0.1700
Data Index: 8245159 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8543. Min Range: -3.8543
Max Act: 3.8230. Min Act: -0.1700
Data Index: 8245160 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8543. Min Range: -3.8543
Max Act: 3.6979. Min Act: -0.1700
Data Index: 3520680 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8543. Min Range: -3.8543
Max Act: 3.6353. Min Act: -0.1700
Data Index: 1441238 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8543. Min Range: -3.8543
Max Act: 3.6040. Min Act: -0.1700
Data Index: 6432635 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8543. Min Range: -3.8543
Max Act: 3.5100. Min Act: -0.1700
Data Index: 498986 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8543. Min Range: -3.8543
Max Act: 3.5100. Min Act: -0.1700
Data Index: 5561703 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8543. Min Range: -3.8543
Max Act: 3.4787. Min Act: -0.1700
Data Index: 643792 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8543. Min Range: -3.8543
Max Act: 3.4787. Min Act: -0.1693
Data Index: 518258 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8543. Min Range: -3.8543
Max Act: 3.4787. Min Act: -0.1700
Data Index: 2509209 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8543. Min Range: -3.8543
Max Act: 3.4787. Min Act: -0.1700
Data Index: 4848246 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8543. Min Range: -3.8543
Max Act: 3.4787. Min Act: -0.1700
Data Index: 367259 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8543. Min Range: -3.8543
Max Act: 3.4474. Min Act: -0.1700
Data Index: 522614 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8543. Min Range: -3.8543
Max Act: 3.4474. Min Act: -0.1700
Data Index: 7829611 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8543. Min Range: -3.8543
Max Act: 3.4160. Min Act: -0.1700
Data Index: 5376297 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8543. Min Range: -3.8543
Max Act: 3.4474. Min Act: -0.1700
Data Index: 5260071 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8543. Min Range: -3.8543
Max Act: 3.3847. Min Act: -0.1700
Data Index: 3964103 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8543. Min Range: -3.8543
Max Act: 3.3847. Min Act: -0.1700
Data Index: 5278645 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8543. Min Range: -3.8543
Max Act: 3.4160. Min Act: -0.1700
Data Index: 6019785 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19