Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1552 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6330. Min Range: -2.6330
Max Act: 2.6330. Min Act: -0.1700
Data Index: 4789059 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6330. Min Range: -2.6330
Max Act: 2.6008. Min Act: -0.1700
Data Index: 5827599 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6330. Min Range: -2.6330
Max Act: 2.5525. Min Act: -0.1700
Data Index: 2652004 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6330. Min Range: -2.6330
Max Act: 2.5202. Min Act: -0.1700
Data Index: 2216297 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6330. Min Range: -2.6330
Max Act: 2.5363. Min Act: -0.1700
Data Index: 6912252 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6330. Min Range: -2.6330
Max Act: 2.5040. Min Act: -0.1700
Data Index: 5112042 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6330. Min Range: -2.6330
Max Act: 2.5202. Min Act: -0.1700
Data Index: 1771414 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6330. Min Range: -2.6330
Max Act: 2.5040. Min Act: -0.1700
Data Index: 2410795 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6330. Min Range: -2.6330
Max Act: 2.5202. Min Act: -0.1700
Data Index: 1726055 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6330. Min Range: -2.6330
Max Act: 2.5040. Min Act: -0.1700
Data Index: 1565856 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6330. Min Range: -2.6330
Max Act: 2.4878. Min Act: -0.1700
Data Index: 8294739 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6330. Min Range: -2.6330
Max Act: 2.4715. Min Act: -0.1700
Data Index: 2904911 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6330. Min Range: -2.6330
Max Act: 2.4878. Min Act: -0.1700
Data Index: 1765260 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6330. Min Range: -2.6330
Max Act: 2.4715. Min Act: -0.1700
Data Index: 8152257 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6330. Min Range: -2.6330
Max Act: 2.4715. Min Act: -0.1700
Data Index: 2620225 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6330. Min Range: -2.6330
Max Act: 2.4553. Min Act: -0.1700
Data Index: 548487 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6330. Min Range: -2.6330
Max Act: 2.4715. Min Act: -0.1700
Data Index: 2428968 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6330. Min Range: -2.6330
Max Act: 2.4878. Min Act: -0.1700
Data Index: 5869260 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6330. Min Range: -2.6330
Max Act: 2.4715. Min Act: -0.1700
Data Index: 1876332 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6330. Min Range: -2.6330
Max Act: 2.4878. Min Act: -0.1700
Data Index: 5139306 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19