Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3529 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7543. Min Range: -5.7543
Max Act: 5.7543. Min Act: -0.1700
Data Index: 7645620 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7543. Min Range: -5.7543
Max Act: 5.6918. Min Act: -0.1700
Data Index: 5107831 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7543. Min Range: -5.7543
Max Act: 5.6293. Min Act: -0.1700
Data Index: 7682911 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7543. Min Range: -5.7543
Max Act: 5.5981. Min Act: -0.1700
Data Index: 7044553 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7543. Min Range: -5.7543
Max Act: 5.5356. Min Act: -0.1700
Data Index: 5107832 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7543. Min Range: -5.7543
Max Act: 5.5043. Min Act: -0.1700
Data Index: 5101572 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7543. Min Range: -5.7543
Max Act: 5.4418. Min Act: -0.1700
Data Index: 3746743 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7543. Min Range: -5.7543
Max Act: 5.3793. Min Act: -0.1700
Data Index: 6172244 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7543. Min Range: -5.7543
Max Act: 5.3481. Min Act: -0.1700
Data Index: 4617075 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7543. Min Range: -5.7543
Max Act: 5.2231. Min Act: -0.1700
Data Index: 4639368 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7543. Min Range: -5.7543
Max Act: 5.2543. Min Act: -0.1700
Data Index: 5812567 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7543. Min Range: -5.7543
Max Act: 5.2231. Min Act: -0.1700
Data Index: 988672 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7543. Min Range: -5.7543
Max Act: 5.2231. Min Act: -0.1700
Data Index: 7826696 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7543. Min Range: -5.7543
Max Act: 5.1606. Min Act: -0.1700
Data Index: 5988594 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7543. Min Range: -5.7543
Max Act: 5.1293. Min Act: -0.1700
Data Index: 2961448 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7543. Min Range: -5.7543
Max Act: 5.1293. Min Act: -0.1700
Data Index: 6348567 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7543. Min Range: -5.7543
Max Act: 5.0668. Min Act: -0.1700
Data Index: 2327821 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7543. Min Range: -5.7543
Max Act: 5.0981. Min Act: -0.1700
Data Index: 88325 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7543. Min Range: -5.7543
Max Act: 5.0981. Min Act: -0.1700
Data Index: 2376000 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7543. Min Range: -5.7543
Max Act: 5.0981. Min Act: -0.1700
Data Index: 3566960 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19