Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3076 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8732. Min Range: -5.8732
Max Act: 5.8732. Min Act: -0.1700
Data Index: 8110737 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8732. Min Range: -5.8732
Max Act: 5.8107. Min Act: -0.1700
Data Index: 8389735 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8732. Min Range: -5.8732
Max Act: 5.8107. Min Act: -0.1700
Data Index: 8303139 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8732. Min Range: -5.8732
Max Act: 5.7794. Min Act: -0.1700
Data Index: 4955370 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8732. Min Range: -5.8732
Max Act: 5.7482. Min Act: -0.1700
Data Index: 411353 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8732. Min Range: -5.8732
Max Act: 5.7169. Min Act: -0.1700
Data Index: 3451241 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8732. Min Range: -5.8732
Max Act: 5.6857. Min Act: -0.1700
Data Index: 5193747 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8732. Min Range: -5.8732
Max Act: 5.6544. Min Act: -0.1700
Data Index: 7229775 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8732. Min Range: -5.8732
Max Act: 5.6544. Min Act: -0.1700
Data Index: 5885127 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8732. Min Range: -5.8732
Max Act: 5.6544. Min Act: -0.1700
Data Index: 4984136 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8732. Min Range: -5.8732
Max Act: 5.6544. Min Act: -0.1700
Data Index: 3085600 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8732. Min Range: -5.8732
Max Act: 5.6232. Min Act: -0.1700
Data Index: 1783544 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8732. Min Range: -5.8732
Max Act: 5.5919. Min Act: -0.1700
Data Index: 7465056 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8732. Min Range: -5.8732
Max Act: 5.5919. Min Act: -0.1700
Data Index: 5392681 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8732. Min Range: -5.8732
Max Act: 5.5607. Min Act: -0.1700
Data Index: 5815356 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8732. Min Range: -5.8732
Max Act: 5.5607. Min Act: -0.1700
Data Index: 6738847 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8732. Min Range: -5.8732
Max Act: 5.5607. Min Act: -0.1700
Data Index: 894148 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8732. Min Range: -5.8732
Max Act: 5.5607. Min Act: -0.1700
Data Index: 3054368 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8732. Min Range: -5.8732
Max Act: 5.5607. Min Act: -0.1700
Data Index: 6398199 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8732. Min Range: -5.8732
Max Act: 5.5919. Min Act: -0.1700
Data Index: 31318 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19