Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4253 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2615. Min Range: -6.2615
Max Act: 6.2615. Min Act: -0.1700
Data Index: 2120109 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2615. Min Range: -6.2615
Max Act: 6.2615. Min Act: -0.1700
Data Index: 7036037 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2615. Min Range: -6.2615
Max Act: 6.1052. Min Act: -0.1700
Data Index: 7036039 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2615. Min Range: -6.2615
Max Act: 6.0740. Min Act: -0.1700
Data Index: 5247583 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.9802. Min Act: -0.1700
Data Index: 8536718 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.9177. Min Act: -0.1700
Data Index: 1666118 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.8240. Min Act: -0.1700
Data Index: 5200403 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.7927. Min Act: -0.1700
Data Index: 2822564 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.7927. Min Act: -0.1700
Data Index: 1322547 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.7615. Min Act: -0.1700
Data Index: 2227138 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.7615. Min Act: -0.1700
Data Index: 1143811 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.7615. Min Act: -0.1700
Data Index: 8312551 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.7302. Min Act: -0.1700
Data Index: 8436266 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.6990. Min Act: -0.1700
Data Index: 1304347 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.6990. Min Act: -0.1700
Data Index: 8684940 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.6990. Min Act: -0.1700
Data Index: 8312566 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.6990. Min Act: -0.1700
Data Index: 2628776 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.6990. Min Act: -0.1700
Data Index: 4176612 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.6677. Min Act: -0.1700
Data Index: 7971853 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2615. Min Range: -6.2615
Max Act: 5.6677. Min Act: -0.1700
Data Index: 3680772 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19