Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4788 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4201. Min Range: -7.4201
Max Act: 7.4201. Min Act: -0.1700
Data Index: 1080982 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4201. Min Range: -7.4201
Max Act: 7.3576. Min Act: -0.1700
Data Index: 1752473 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4201. Min Range: -7.4201
Max Act: 7.0764. Min Act: -0.1700
Data Index: 7965890 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4201. Min Range: -7.4201
Max Act: 7.0764. Min Act: -0.1700
Data Index: 1272856 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4201. Min Range: -7.4201
Max Act: 7.0451. Min Act: -0.1700
Data Index: 2718966 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4201. Min Range: -7.4201
Max Act: 7.0451. Min Act: -0.1700
Data Index: 4787518 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4201. Min Range: -7.4201
Max Act: 7.0139. Min Act: -0.1700
Data Index: 7490957 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4201. Min Range: -7.4201
Max Act: 6.9826. Min Act: -0.1700
Data Index: 1418146 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4201. Min Range: -7.4201
Max Act: 6.9514. Min Act: -0.1700
Data Index: 7833 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4201. Min Range: -7.4201
Max Act: 6.8889. Min Act: -0.1700
Data Index: 6318756 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4201. Min Range: -7.4201
Max Act: 6.8889. Min Act: -0.1700
Data Index: 7317784 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4201. Min Range: -7.4201
Max Act: 6.8889. Min Act: -0.1700
Data Index: 4613211 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4201. Min Range: -7.4201
Max Act: 6.8576. Min Act: -0.1700
Data Index: 5629679 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4201. Min Range: -7.4201
Max Act: 6.8889. Min Act: -0.1700
Data Index: 900308 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4201. Min Range: -7.4201
Max Act: 6.8889. Min Act: -0.1700
Data Index: 5383825 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4201. Min Range: -7.4201
Max Act: 6.8264. Min Act: -0.1700
Data Index: 1262039 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4201. Min Range: -7.4201
Max Act: 6.8576. Min Act: -0.1700
Data Index: 1419035 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4201. Min Range: -7.4201
Max Act: 6.8264. Min Act: -0.1700
Data Index: 4518577 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4201. Min Range: -7.4201
Max Act: 6.8264. Min Act: -0.1700
Data Index: 5071628 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4201. Min Range: -7.4201
Max Act: 6.8264. Min Act: -0.1700
Data Index: 1297465 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19