Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2742 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2131. Min Range: -6.2131
Max Act: 6.2131. Min Act: -0.1700
Data Index: 338355 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2131. Min Range: -6.2131
Max Act: 6.0569. Min Act: -0.1700
Data Index: 2218248 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2131. Min Range: -6.2131
Max Act: 5.9319. Min Act: -0.1700
Data Index: 7540253 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2131. Min Range: -6.2131
Max Act: 5.9006. Min Act: -0.1700
Data Index: 4959467 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2131. Min Range: -6.2131
Max Act: 5.9006. Min Act: -0.1700
Data Index: 3736988 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2131. Min Range: -6.2131
Max Act: 5.9006. Min Act: -0.1700
Data Index: 4694252 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2131. Min Range: -6.2131
Max Act: 5.9006. Min Act: -0.1700
Data Index: 4198352 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2131. Min Range: -6.2131
Max Act: 5.9006. Min Act: -0.1700
Data Index: 1686708 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2131. Min Range: -6.2131
Max Act: 5.8694. Min Act: -0.1700
Data Index: 6855265 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2131. Min Range: -6.2131
Max Act: 5.8694. Min Act: -0.1700
Data Index: 454035 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2131. Min Range: -6.2131
Max Act: 5.8694. Min Act: -0.1700
Data Index: 2453345 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2131. Min Range: -6.2131
Max Act: 5.8381. Min Act: -0.1700
Data Index: 8104751 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2131. Min Range: -6.2131
Max Act: 5.8381. Min Act: -0.1700
Data Index: 675714 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2131. Min Range: -6.2131
Max Act: 5.8381. Min Act: -0.1700
Data Index: 4315373 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2131. Min Range: -6.2131
Max Act: 5.8381. Min Act: -0.1700
Data Index: 1529450 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2131. Min Range: -6.2131
Max Act: 5.8381. Min Act: -0.1699
Data Index: 1277239 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2131. Min Range: -6.2131
Max Act: 5.8381. Min Act: -0.1700
Data Index: 3007617 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2131. Min Range: -6.2131
Max Act: 5.8381. Min Act: -0.1700
Data Index: 2610481 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2131. Min Range: -6.2131
Max Act: 5.8069. Min Act: -0.1700
Data Index: 47818 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2131. Min Range: -6.2131
Max Act: 5.8069. Min Act: -0.1700
Data Index: 2652116 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19