Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 833 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8181. Min Range: -5.8181
Max Act: 5.8181. Min Act: -0.1112
Data Index: 3560470 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8181. Min Range: -5.8181
Max Act: 5.7556. Min Act: -0.1689
Data Index: 3108586 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8181. Min Range: -5.8181
Max Act: 5.6931. Min Act: -0.0748
Data Index: 2134568 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8181. Min Range: -5.8181
Max Act: 5.6931. Min Act: -0.0748
Data Index: 8257211 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8181. Min Range: -5.8181
Max Act: 5.6618. Min Act: -0.1364
Data Index: 3108577 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8181. Min Range: -5.8181
Max Act: 5.6931. Min Act: -0.1474
Data Index: 8653808 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8181. Min Range: -5.8181
Max Act: 5.6931. Min Act: -0.1586
Data Index: 3560452 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8181. Min Range: -5.8181
Max Act: 5.6931. Min Act: -0.1657
Data Index: 7122749 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8181. Min Range: -5.8181
Max Act: 5.6618. Min Act: -0.1662
Data Index: 1443524 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8181. Min Range: -5.8181
Max Act: 5.6618. Min Act: -0.1552
Data Index: 28538 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8181. Min Range: -5.8181
Max Act: 5.6618. Min Act: -0.1187
Data Index: 7191515 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8181. Min Range: -5.8181
Max Act: 5.6931. Min Act: -0.1585
Data Index: 5657923 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8181. Min Range: -5.8181
Max Act: 5.6618. Min Act: -0.1613
Data Index: 3605306 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8181. Min Range: -5.8181
Max Act: 5.6618. Min Act: -0.1564
Data Index: 3605295 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8181. Min Range: -5.8181
Max Act: 5.6618. Min Act: -0.1680
Data Index: 5657907 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8181. Min Range: -5.8181
Max Act: 5.6618. Min Act: -0.1606
Data Index: 1495206 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8181. Min Range: -5.8181
Max Act: 5.6618. Min Act: -0.1642
Data Index: 5704796 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8181. Min Range: -5.8181
Max Act: 5.6306. Min Act: -0.1700
Data Index: 311753 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8181. Min Range: -5.8181
Max Act: 5.6306. Min Act: -0.1700
Data Index: 28525 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8181. Min Range: -5.8181
Max Act: 5.6306. Min Act: -0.1525
Data Index: 4926802 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19