Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3458 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2339. Min Range: -6.2339
Max Act: 6.2339. Min Act: -0.1700
Data Index: 7077117 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2339. Min Range: -6.2339
Max Act: 6.1714. Min Act: -0.1700
Data Index: 1153769 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2339. Min Range: -6.2339
Max Act: 6.1401. Min Act: -0.1700
Data Index: 1193286 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2339. Min Range: -6.2339
Max Act: 5.9214. Min Act: -0.1700
Data Index: 1958410 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2339. Min Range: -6.2339
Max Act: 5.8901. Min Act: -0.1700
Data Index: 4613254 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2339. Min Range: -6.2339
Max Act: 5.8276. Min Act: -0.1700
Data Index: 1212890 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2339. Min Range: -6.2339
Max Act: 5.7651. Min Act: -0.1700
Data Index: 6131310 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2339. Min Range: -6.2339
Max Act: 5.7964. Min Act: -0.1700
Data Index: 486831 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2339. Min Range: -6.2339
Max Act: 5.7964. Min Act: -0.1700
Data Index: 5660600 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2339. Min Range: -6.2339
Max Act: 5.7964. Min Act: -0.1700
Data Index: 7605585 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2339. Min Range: -6.2339
Max Act: 5.7964. Min Act: -0.1700
Data Index: 5496729 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2339. Min Range: -6.2339
Max Act: 5.7964. Min Act: -0.1700
Data Index: 6800599 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2339. Min Range: -6.2339
Max Act: 5.7964. Min Act: -0.1700
Data Index: 2497652 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2339. Min Range: -6.2339
Max Act: 5.7651. Min Act: -0.1700
Data Index: 1377383 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2339. Min Range: -6.2339
Max Act: 5.7651. Min Act: -0.1700
Data Index: 5535679 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2339. Min Range: -6.2339
Max Act: 5.7651. Min Act: -0.1700
Data Index: 7498960 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2339. Min Range: -6.2339
Max Act: 5.7339. Min Act: -0.1700
Data Index: 2286923 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2339. Min Range: -6.2339
Max Act: 5.7339. Min Act: -0.1700
Data Index: 8376861 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2339. Min Range: -6.2339
Max Act: 5.7339. Min Act: -0.1700
Data Index: 6800608 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2339. Min Range: -6.2339
Max Act: 5.7339. Min Act: -0.1700
Data Index: 3513314 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19