Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4787 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.8893. Min Act: -0.1700
Data Index: 2190681 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.7172. Min Act: -0.1700
Data Index: 7801522 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.6234. Min Act: -0.1700
Data Index: 4734770 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.5921. Min Act: -0.1700
Data Index: 7064820 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.5764. Min Act: -0.1700
Data Index: 4134710 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.5921. Min Act: -0.1700
Data Index: 4122742 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.5608. Min Act: -0.1700
Data Index: 7224960 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.5608. Min Act: -0.1700
Data Index: 3900984 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.5608. Min Act: -0.1700
Data Index: 5386522 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.5451. Min Act: -0.1700
Data Index: 1485850 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.5451. Min Act: -0.1700
Data Index: 725805 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.5295. Min Act: -0.1700
Data Index: 7086537 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.5295. Min Act: -0.1700
Data Index: 2261191 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.5295. Min Act: -0.1700
Data Index: 2743405 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.5295. Min Act: -0.1700
Data Index: 3764142 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.5138. Min Act: -0.1700
Data Index: 3745073 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.5138. Min Act: -0.1700
Data Index: 1648918 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.5138. Min Act: -0.1700
Data Index: 5312288 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.5138. Min Act: -0.1700
Data Index: 8825560 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8893. Min Range: -3.8893
Max Act: 3.5138. Min Act: -0.1700
Data Index: 8564432 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19