Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2984 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3970. Min Range: -6.3970
Max Act: 6.3970. Min Act: -0.1700
Data Index: 8394232 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3970. Min Range: -6.3970
Max Act: 6.3970. Min Act: -0.1700
Data Index: 3746602 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3970. Min Range: -6.3970
Max Act: 6.3657. Min Act: -0.1700
Data Index: 8414143 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3970. Min Range: -6.3970
Max Act: 6.3657. Min Act: -0.1700
Data Index: 5051943 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3970. Min Range: -6.3970
Max Act: 6.3345. Min Act: -0.1700
Data Index: 8261517 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3970. Min Range: -6.3970
Max Act: 6.2720. Min Act: -0.1700
Data Index: 6563193 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3970. Min Range: -6.3970
Max Act: 6.2095. Min Act: -0.1700
Data Index: 6406724 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3970. Min Range: -6.3970
Max Act: 6.2095. Min Act: -0.1700
Data Index: 97426 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3970. Min Range: -6.3970
Max Act: 6.1470. Min Act: -0.1700
Data Index: 5026579 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3970. Min Range: -6.3970
Max Act: 6.1782. Min Act: -0.1700
Data Index: 3826595 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3970. Min Range: -6.3970
Max Act: 6.1470. Min Act: -0.1700
Data Index: 4616708 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3970. Min Range: -6.3970
Max Act: 6.1157. Min Act: -0.1700
Data Index: 4838054 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3970. Min Range: -6.3970
Max Act: 6.0532. Min Act: -0.1700
Data Index: 5170416 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3970. Min Range: -6.3970
Max Act: 6.0532. Min Act: -0.1700
Data Index: 8430456 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3970. Min Range: -6.3970
Max Act: 6.0220. Min Act: -0.1700
Data Index: 5853147 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3970. Min Range: -6.3970
Max Act: 6.0220. Min Act: -0.1700
Data Index: 7680144 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3970. Min Range: -6.3970
Max Act: 6.0220. Min Act: -0.1700
Data Index: 1929084 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3970. Min Range: -6.3970
Max Act: 5.9907. Min Act: -0.1700
Data Index: 5819975 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3970. Min Range: -6.3970
Max Act: 5.9907. Min Act: -0.1700
Data Index: 6492535 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3970. Min Range: -6.3970
Max Act: 5.9907. Min Act: -0.1700
Data Index: 7997840 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19