Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3851 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.6215. Min Act: -0.1700
Data Index: 3798174 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.4653. Min Act: -0.1700
Data Index: 1623342 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.1840. Min Act: -0.1700
Data Index: 2791319 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.0903. Min Act: -0.1700
Data Index: 2815900 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.0903. Min Act: -0.1700
Data Index: 5385718 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.0278. Min Act: -0.1700
Data Index: 7001987 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.0590. Min Act: -0.1700
Data Index: 5901203 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.0590. Min Act: -0.1700
Data Index: 3821621 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.0278. Min Act: -0.1700
Data Index: 8515235 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.0278. Min Act: -0.1700
Data Index: 4658791 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6215. Min Range: -6.6215
Max Act: 5.9965. Min Act: -0.1700
Data Index: 4910335 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6215. Min Range: -6.6215
Max Act: 5.9653. Min Act: -0.1700
Data Index: 1561116 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6215. Min Range: -6.6215
Max Act: 5.9653. Min Act: -0.1700
Data Index: 1097776 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6215. Min Range: -6.6215
Max Act: 5.9340. Min Act: -0.1700
Data Index: 3435308 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6215. Min Range: -6.6215
Max Act: 5.9028. Min Act: -0.1700
Data Index: 550122 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6215. Min Range: -6.6215
Max Act: 5.9340. Min Act: -0.1700
Data Index: 4511501 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6215. Min Range: -6.6215
Max Act: 5.9653. Min Act: -0.1700
Data Index: 705169 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6215. Min Range: -6.6215
Max Act: 5.9028. Min Act: -0.1700
Data Index: 2631798 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6215. Min Range: -6.6215
Max Act: 5.9028. Min Act: -0.1700
Data Index: 7774421 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6215. Min Range: -6.6215
Max Act: 5.8715. Min Act: -0.1700
Data Index: 922310 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19