Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4228 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9125. Min Range: -6.9125
Max Act: 6.9125. Min Act: -0.1700
Data Index: 4436295 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9125. Min Range: -6.9125
Max Act: 6.8500. Min Act: -0.1700
Data Index: 947590 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9125. Min Range: -6.9125
Max Act: 6.8187. Min Act: -0.1700
Data Index: 8416409 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9125. Min Range: -6.9125
Max Act: 6.8187. Min Act: -0.1700
Data Index: 4271506 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9125. Min Range: -6.9125
Max Act: 6.7875. Min Act: -0.1700
Data Index: 4636855 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9125. Min Range: -6.9125
Max Act: 6.7562. Min Act: -0.1700
Data Index: 412728 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9125. Min Range: -6.9125
Max Act: 6.7562. Min Act: -0.1700
Data Index: 3311516 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9125. Min Range: -6.9125
Max Act: 6.7562. Min Act: -0.1700
Data Index: 5321887 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9125. Min Range: -6.9125
Max Act: 6.7250. Min Act: -0.1700
Data Index: 4865212 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9125. Min Range: -6.9125
Max Act: 6.7250. Min Act: -0.1700
Data Index: 2498921 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9125. Min Range: -6.9125
Max Act: 6.7250. Min Act: -0.1700
Data Index: 288246 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9125. Min Range: -6.9125
Max Act: 6.7250. Min Act: -0.1700
Data Index: 6068965 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9125. Min Range: -6.9125
Max Act: 6.7562. Min Act: -0.1700
Data Index: 1645692 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9125. Min Range: -6.9125
Max Act: 6.7250. Min Act: -0.1700
Data Index: 7561353 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9125. Min Range: -6.9125
Max Act: 6.6937. Min Act: -0.1700
Data Index: 2963567 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9125. Min Range: -6.9125
Max Act: 6.6937. Min Act: -0.1700
Data Index: 8781429 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9125. Min Range: -6.9125
Max Act: 6.6937. Min Act: -0.1700
Data Index: 3304636 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9125. Min Range: -6.9125
Max Act: 6.6937. Min Act: -0.1700
Data Index: 167758 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9125. Min Range: -6.9125
Max Act: 6.6937. Min Act: -0.1700
Data Index: 6309873 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9125. Min Range: -6.9125
Max Act: 6.6625. Min Act: -0.1700
Data Index: 391281 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19