Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2903 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4688. Min Range: -3.4688
Max Act: 3.4688. Min Act: -0.1700
Data Index: 4831389 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4688. Min Range: -3.4688
Max Act: 3.3747. Min Act: -0.1700
Data Index: 553876 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4688. Min Range: -3.4688
Max Act: 3.3433. Min Act: -0.1700
Data Index: 1355378 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4688. Min Range: -3.4688
Max Act: 3.3433. Min Act: -0.1700
Data Index: 6680233 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4688. Min Range: -3.4688
Max Act: 3.3433. Min Act: -0.1700
Data Index: 8780696 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4688. Min Range: -3.4688
Max Act: 3.3433. Min Act: -0.1700
Data Index: 3398164 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4688. Min Range: -3.4688
Max Act: 3.3433. Min Act: -0.1700
Data Index: 6987510 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4688. Min Range: -3.4688
Max Act: 3.3433. Min Act: -0.1700
Data Index: 6923634 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4688. Min Range: -3.4688
Max Act: 3.3120. Min Act: -0.1700
Data Index: 7741502 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4688. Min Range: -3.4688
Max Act: 3.3120. Min Act: -0.1700
Data Index: 3265020 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4688. Min Range: -3.4688
Max Act: 3.3433. Min Act: -0.1700
Data Index: 6361095 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4688. Min Range: -3.4688
Max Act: 3.3120. Min Act: -0.1700
Data Index: 4021542 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4688. Min Range: -3.4688
Max Act: 3.3120. Min Act: -0.1700
Data Index: 3581305 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4688. Min Range: -3.4688
Max Act: 3.2806. Min Act: -0.1700
Data Index: 3810038 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4688. Min Range: -3.4688
Max Act: 3.2806. Min Act: -0.1700
Data Index: 2934914 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4688. Min Range: -3.4688
Max Act: 3.2806. Min Act: -0.1700
Data Index: 3492618 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4688. Min Range: -3.4688
Max Act: 3.2806. Min Act: -0.1700
Data Index: 2952129 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4688. Min Range: -3.4688
Max Act: 3.2806. Min Act: -0.1700
Data Index: 118767 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4688. Min Range: -3.4688
Max Act: 3.2806. Min Act: -0.1700
Data Index: 3866763 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4688. Min Range: -3.4688
Max Act: 3.2806. Min Act: -0.1700
Data Index: 3106669 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19