Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 325 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.5356. Min Act: -0.1700
Data Index: 5142750 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.4106. Min Act: -0.1700
Data Index: 5542701 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.3168. Min Act: -0.1700
Data Index: 5968927 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.3168. Min Act: -0.1700
Data Index: 4087776 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.2856. Min Act: -0.1700
Data Index: 1504959 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.2856. Min Act: -0.1700
Data Index: 1966410 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.2231. Min Act: -0.1700
Data Index: 5018075 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1918. Min Act: -0.1700
Data Index: 392162 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1918. Min Act: -0.1700
Data Index: 6823899 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1606. Min Act: -0.1700
Data Index: 3457820 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1606. Min Act: -0.1700
Data Index: 5171249 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1918. Min Act: -0.1700
Data Index: 3591426 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1606. Min Act: -0.1700
Data Index: 5286490 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1293. Min Act: -0.1700
Data Index: 1488207 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1293. Min Act: -0.1700
Data Index: 2955624 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.0981. Min Act: -0.1700
Data Index: 1871527 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.1293. Min Act: -0.1700
Data Index: 1148810 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.0981. Min Act: -0.1700
Data Index: 2788023 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.0981. Min Act: -0.1700
Data Index: 1568390 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5356. Min Range: -6.5356
Max Act: 6.0668. Min Act: -0.1700
Data Index: 3872674 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19