Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1703 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.9332. Min Act: -0.1700
Data Index: 446937 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.8394. Min Act: -0.1700
Data Index: 746813 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.7456. Min Act: -0.1700
Data Index: 4720891 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.6519. Min Act: -0.1700
Data Index: 3383008 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.6519. Min Act: -0.1700
Data Index: 2589074 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.6519. Min Act: -0.1700
Data Index: 4611489 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.6519. Min Act: -0.1700
Data Index: 1300018 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.6519. Min Act: -0.1700
Data Index: 8592322 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.6519. Min Act: -0.1700
Data Index: 1935283 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.6206. Min Act: -0.1700
Data Index: 6126049 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.6206. Min Act: -0.1700
Data Index: 1417150 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.5894. Min Act: -0.1700
Data Index: 2865083 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.5894. Min Act: -0.1700
Data Index: 4236821 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.5894. Min Act: -0.1700
Data Index: 6423187 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.5894. Min Act: -0.1700
Data Index: 5899463 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.5894. Min Act: -0.1700
Data Index: 5325462 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.5894. Min Act: -0.1700
Data Index: 277709 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.5894. Min Act: -0.1700
Data Index: 6691035 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.5269. Min Act: -0.1700
Data Index: 2193645 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9332. Min Range: -4.9332
Max Act: 4.5894. Min Act: -0.1700
Data Index: 6321724 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19