Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4526 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3559. Min Range: -7.3559
Max Act: 7.3559. Min Act: -0.1700
Data Index: 5709485 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3559. Min Range: -7.3559
Max Act: 7.2621. Min Act: -0.1700
Data Index: 161816 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3559. Min Range: -7.3559
Max Act: 7.1996. Min Act: -0.1700
Data Index: 7976541 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3559. Min Range: -7.3559
Max Act: 7.1684. Min Act: -0.1700
Data Index: 4495506 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3559. Min Range: -7.3559
Max Act: 7.0746. Min Act: -0.1700
Data Index: 2255856 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3559. Min Range: -7.3559
Max Act: 7.0746. Min Act: -0.1700
Data Index: 7831251 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3559. Min Range: -7.3559
Max Act: 7.0746. Min Act: -0.1700
Data Index: 4870545 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3559. Min Range: -7.3559
Max Act: 7.0434. Min Act: -0.1700
Data Index: 4883686 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3559. Min Range: -7.3559
Max Act: 7.0746. Min Act: -0.1700
Data Index: 3574811 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3559. Min Range: -7.3559
Max Act: 6.9809. Min Act: -0.1700
Data Index: 4331129 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3559. Min Range: -7.3559
Max Act: 6.9809. Min Act: -0.1700
Data Index: 4045757 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3559. Min Range: -7.3559
Max Act: 6.9809. Min Act: -0.1700
Data Index: 3049394 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3559. Min Range: -7.3559
Max Act: 6.9809. Min Act: -0.1700
Data Index: 1249464 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3559. Min Range: -7.3559
Max Act: 6.9809. Min Act: -0.1700
Data Index: 6334466 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3559. Min Range: -7.3559
Max Act: 6.9809. Min Act: -0.1700
Data Index: 2484984 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3559. Min Range: -7.3559
Max Act: 6.9809. Min Act: -0.1700
Data Index: 3767448 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3559. Min Range: -7.3559
Max Act: 6.9809. Min Act: -0.1699
Data Index: 593553 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3559. Min Range: -7.3559
Max Act: 6.9809. Min Act: -0.1700
Data Index: 4715890 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3559. Min Range: -7.3559
Max Act: 6.9809. Min Act: -0.1700
Data Index: 6213160 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3559. Min Range: -7.3559
Max Act: 6.9809. Min Act: -0.1700
Data Index: 47209 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19