Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3264 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6606. Min Range: -6.6606
Max Act: 6.6606. Min Act: -0.1700
Data Index: 7884831 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6606. Min Range: -6.6606
Max Act: 6.5981. Min Act: -0.1700
Data Index: 169533 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6606. Min Range: -6.6606
Max Act: 6.5043. Min Act: -0.1700
Data Index: 5795613 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6606. Min Range: -6.6606
Max Act: 6.4106. Min Act: -0.1700
Data Index: 3962751 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6606. Min Range: -6.6606
Max Act: 6.3793. Min Act: -0.1700
Data Index: 4195028 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6606. Min Range: -6.6606
Max Act: 6.3168. Min Act: -0.1700
Data Index: 1829882 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6606. Min Range: -6.6606
Max Act: 6.2543. Min Act: -0.1700
Data Index: 7647412 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6606. Min Range: -6.6606
Max Act: 6.2543. Min Act: -0.1700
Data Index: 7576424 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6606. Min Range: -6.6606
Max Act: 6.1293. Min Act: -0.1700
Data Index: 3159246 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6606. Min Range: -6.6606
Max Act: 6.1293. Min Act: -0.1700
Data Index: 7094361 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6606. Min Range: -6.6606
Max Act: 6.1293. Min Act: -0.1700
Data Index: 2491103 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6606. Min Range: -6.6606
Max Act: 6.0981. Min Act: -0.1700
Data Index: 1004345 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6606. Min Range: -6.6606
Max Act: 6.0668. Min Act: -0.1700
Data Index: 8294193 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6606. Min Range: -6.6606
Max Act: 6.0356. Min Act: -0.1700
Data Index: 6122963 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6606. Min Range: -6.6606
Max Act: 5.9731. Min Act: -0.1700
Data Index: 2085315 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6606. Min Range: -6.6606
Max Act: 6.0043. Min Act: -0.1700
Data Index: 1361031 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6606. Min Range: -6.6606
Max Act: 5.9731. Min Act: -0.1700
Data Index: 6399064 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6606. Min Range: -6.6606
Max Act: 5.9418. Min Act: -0.1700
Data Index: 3513268 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6606. Min Range: -6.6606
Max Act: 5.9731. Min Act: -0.1700
Data Index: 5556431 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6606. Min Range: -6.6606
Max Act: 6.0043. Min Act: -0.1700
Data Index: 1007687 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19