Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4715 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0307. Min Range: -3.0307
Max Act: 3.0307. Min Act: -0.1696
Data Index: 8777051 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0307. Min Range: -3.0307
Max Act: 3.0307. Min Act: -0.1666
Data Index: 5860701 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0307. Min Range: -3.0307
Max Act: 2.9992. Min Act: -0.1643
Data Index: 2647534 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0307. Min Range: -3.0307
Max Act: 2.9675. Min Act: -0.1694
Data Index: 8557415 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0307. Min Range: -3.0307
Max Act: 2.8407. Min Act: -0.1666
Data Index: 1004291 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0307. Min Range: -3.0307
Max Act: 2.8724. Min Act: -0.1677
Data Index: 3062688 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0307. Min Range: -3.0307
Max Act: 2.8724. Min Act: -0.1690
Data Index: 1404513 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0307. Min Range: -3.0307
Max Act: 2.8724. Min Act: -0.1700
Data Index: 5123220 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0307. Min Range: -3.0307
Max Act: 2.8407. Min Act: -0.1688
Data Index: 8202899 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0307. Min Range: -3.0307
Max Act: 2.8407. Min Act: -0.1699
Data Index: 5334725 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0307. Min Range: -3.0307
Max Act: 2.8089. Min Act: -0.1695
Data Index: 8608059 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0307. Min Range: -3.0307
Max Act: 2.8089. Min Act: -0.1694
Data Index: 1656434 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0307. Min Range: -3.0307
Max Act: 2.8089. Min Act: -0.1682
Data Index: 5879452 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0307. Min Range: -3.0307
Max Act: 2.8089. Min Act: -0.1700
Data Index: 2703328 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0307. Min Range: -3.0307
Max Act: 2.8089. Min Act: -0.1694
Data Index: 8573595 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0307. Min Range: -3.0307
Max Act: 2.8407. Min Act: -0.1670
Data Index: 1375969 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0307. Min Range: -3.0307
Max Act: 2.8089. Min Act: -0.1697
Data Index: 4996647 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0307. Min Range: -3.0307
Max Act: 2.8089. Min Act: -0.1696
Data Index: 8020434 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0307. Min Range: -3.0307
Max Act: 2.8089. Min Act: -0.1433
Data Index: 86899 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0307. Min Range: -3.0307
Max Act: 2.8089. Min Act: -0.1699
Data Index: 6662379 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19