Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2347 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3726. Min Range: -5.3726
Max Act: 5.3726. Min Act: -0.1700
Data Index: 338741 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3726. Min Range: -5.3726
Max Act: 5.3726. Min Act: -0.1700
Data Index: 7218444 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3726. Min Range: -5.3726
Max Act: 5.3726. Min Act: -0.1700
Data Index: 7604984 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3726. Min Range: -5.3726
Max Act: 5.3726. Min Act: -0.1700
Data Index: 7812961 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3726. Min Range: -5.3726
Max Act: 5.3726. Min Act: -0.1700
Data Index: 4199910 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3726. Min Range: -5.3726
Max Act: 5.3726. Min Act: -0.1700
Data Index: 2025764 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3726. Min Range: -5.3726
Max Act: 5.3413. Min Act: -0.1700
Data Index: 98409 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3726. Min Range: -5.3726
Max Act: 5.3413. Min Act: -0.1700
Data Index: 7670976 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3726. Min Range: -5.3726
Max Act: 5.3413. Min Act: -0.1700
Data Index: 6105241 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3726. Min Range: -5.3726
Max Act: 5.3101. Min Act: -0.1700
Data Index: 3062098 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3726. Min Range: -5.3726
Max Act: 5.3101. Min Act: -0.1700
Data Index: 1435481 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3726. Min Range: -5.3726
Max Act: 5.3101. Min Act: -0.1700
Data Index: 3365104 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3726. Min Range: -5.3726
Max Act: 5.3101. Min Act: -0.1700
Data Index: 3449917 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3726. Min Range: -5.3726
Max Act: 5.3413. Min Act: -0.1700
Data Index: 6562741 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3726. Min Range: -5.3726
Max Act: 5.3101. Min Act: -0.1700
Data Index: 1925432 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3726. Min Range: -5.3726
Max Act: 5.2788. Min Act: -0.1700
Data Index: 6868448 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3726. Min Range: -5.3726
Max Act: 5.2476. Min Act: -0.1700
Data Index: 933124 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3726. Min Range: -5.3726
Max Act: 5.2788. Min Act: -0.1700
Data Index: 705695 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3726. Min Range: -5.3726
Max Act: 5.2788. Min Act: -0.1700
Data Index: 5891544 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3726. Min Range: -5.3726
Max Act: 5.2788. Min Act: -0.1700
Data Index: 5251166 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19