Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 146 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4083. Min Range: -5.4083
Max Act: 5.4083. Min Act: -0.1700
Data Index: 8818675 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4083. Min Range: -5.4083
Max Act: 5.1896. Min Act: -0.1700
Data Index: 7904512 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4083. Min Range: -5.4083
Max Act: 5.1896. Min Act: -0.1700
Data Index: 4557526 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4083. Min Range: -5.4083
Max Act: 5.1583. Min Act: -0.1700
Data Index: 7964758 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4083. Min Range: -5.4083
Max Act: 5.1583. Min Act: -0.1700
Data Index: 977753 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4083. Min Range: -5.4083
Max Act: 5.1271. Min Act: -0.1700
Data Index: 2772476 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4083. Min Range: -5.4083
Max Act: 5.0958. Min Act: -0.1700
Data Index: 8787124 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4083. Min Range: -5.4083
Max Act: 5.0958. Min Act: -0.1700
Data Index: 4991906 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4083. Min Range: -5.4083
Max Act: 5.0958. Min Act: -0.1700
Data Index: 2336577 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4083. Min Range: -5.4083
Max Act: 5.0958. Min Act: -0.1700
Data Index: 6737845 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4083. Min Range: -5.4083
Max Act: 5.0646. Min Act: -0.1700
Data Index: 3169414 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4083. Min Range: -5.4083
Max Act: 5.0646. Min Act: -0.1700
Data Index: 1506244 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4083. Min Range: -5.4083
Max Act: 5.0646. Min Act: -0.1700
Data Index: 1742962 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4083. Min Range: -5.4083
Max Act: 5.0646. Min Act: -0.1700
Data Index: 3436640 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4083. Min Range: -5.4083
Max Act: 5.0021. Min Act: -0.1700
Data Index: 8174919 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4083. Min Range: -5.4083
Max Act: 5.0021. Min Act: -0.1700
Data Index: 2080731 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4083. Min Range: -5.4083
Max Act: 5.0333. Min Act: -0.1700
Data Index: 5922097 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4083. Min Range: -5.4083
Max Act: 5.0333. Min Act: -0.1700
Data Index: 7455002 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4083. Min Range: -5.4083
Max Act: 5.0333. Min Act: -0.1700
Data Index: 7768302 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4083. Min Range: -5.4083
Max Act: 5.0021. Min Act: -0.1700
Data Index: 1827387 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19