Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4046 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9608. Min Range: -5.9608
Max Act: 5.9608. Min Act: -0.1700
Data Index: 25975 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9608. Min Range: -5.9608
Max Act: 5.8983. Min Act: -0.1700
Data Index: 3251376 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9608. Min Range: -5.9608
Max Act: 5.8671. Min Act: -0.1700
Data Index: 6084078 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9608. Min Range: -5.9608
Max Act: 5.8358. Min Act: -0.1700
Data Index: 4045035 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9608. Min Range: -5.9608
Max Act: 5.8046. Min Act: -0.1700
Data Index: 7942752 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9608. Min Range: -5.9608
Max Act: 5.7421. Min Act: -0.1700
Data Index: 4632421 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9608. Min Range: -5.9608
Max Act: 5.6796. Min Act: -0.1700
Data Index: 3037120 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9608. Min Range: -5.9608
Max Act: 5.6483. Min Act: -0.1700
Data Index: 806354 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9608. Min Range: -5.9608
Max Act: 5.6171. Min Act: -0.1700
Data Index: 3349099 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9608. Min Range: -5.9608
Max Act: 5.6171. Min Act: -0.1700
Data Index: 2620219 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9608. Min Range: -5.9608
Max Act: 5.6171. Min Act: -0.1700
Data Index: 4340790 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9608. Min Range: -5.9608
Max Act: 5.5858. Min Act: -0.1700
Data Index: 4553580 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9608. Min Range: -5.9608
Max Act: 5.5546. Min Act: -0.1700
Data Index: 67138 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9608. Min Range: -5.9608
Max Act: 5.6171. Min Act: -0.1700
Data Index: 7930434 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9608. Min Range: -5.9608
Max Act: 5.5546. Min Act: -0.1700
Data Index: 25981 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9608. Min Range: -5.9608
Max Act: 5.5546. Min Act: -0.1700
Data Index: 6592838 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9608. Min Range: -5.9608
Max Act: 5.5233. Min Act: -0.1700
Data Index: 1789710 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9608. Min Range: -5.9608
Max Act: 5.4921. Min Act: -0.1700
Data Index: 3597544 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9608. Min Range: -5.9608
Max Act: 5.5233. Min Act: -0.1700
Data Index: 4458469 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9608. Min Range: -5.9608
Max Act: 5.4921. Min Act: -0.1700
Data Index: 5123588 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19