Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3500 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3627. Min Range: -4.3627
Max Act: 4.3627. Min Act: -0.1700
Data Index: 4608374 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3627. Min Range: -4.3627
Max Act: 4.3002. Min Act: -0.1700
Data Index: 6382036 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3627. Min Range: -4.3627
Max Act: 4.3002. Min Act: -0.1700
Data Index: 6917351 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3627. Min Range: -4.3627
Max Act: 4.2689. Min Act: -0.1700
Data Index: 5738200 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3627. Min Range: -4.3627
Max Act: 4.2689. Min Act: -0.1700
Data Index: 3867037 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3627. Min Range: -4.3627
Max Act: 4.2689. Min Act: -0.1700
Data Index: 5931402 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3627. Min Range: -4.3627
Max Act: 4.2689. Min Act: -0.1700
Data Index: 5426697 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3627. Min Range: -4.3627
Max Act: 4.2377. Min Act: -0.1700
Data Index: 7299940 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3627. Min Range: -4.3627
Max Act: 4.2377. Min Act: -0.1700
Data Index: 3766134 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3627. Min Range: -4.3627
Max Act: 4.2064. Min Act: -0.1700
Data Index: 5400355 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3627. Min Range: -4.3627
Max Act: 4.2064. Min Act: -0.1700
Data Index: 1401677 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3627. Min Range: -4.3627
Max Act: 4.2064. Min Act: -0.1700
Data Index: 5341527 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3627. Min Range: -4.3627
Max Act: 4.2064. Min Act: -0.1700
Data Index: 3269750 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3627. Min Range: -4.3627
Max Act: 4.1752. Min Act: -0.1700
Data Index: 6610122 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3627. Min Range: -4.3627
Max Act: 4.2064. Min Act: -0.1700
Data Index: 5384468 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3627. Min Range: -4.3627
Max Act: 4.1752. Min Act: -0.1700
Data Index: 6552731 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3627. Min Range: -4.3627
Max Act: 4.2064. Min Act: -0.1700
Data Index: 4431297 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3627. Min Range: -4.3627
Max Act: 4.2377. Min Act: -0.1700
Data Index: 6415779 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3627. Min Range: -4.3627
Max Act: 4.2377. Min Act: -0.1700
Data Index: 3918022 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3627. Min Range: -4.3627
Max Act: 4.2064. Min Act: -0.1700
Data Index: 3613246 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19