Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2870 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1763. Min Range: -6.1763
Max Act: 6.1763. Min Act: -0.1700
Data Index: 450026 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1763. Min Range: -6.1763
Max Act: 6.0825. Min Act: -0.1700
Data Index: 6309335 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1763. Min Range: -6.1763
Max Act: 5.9888. Min Act: -0.1700
Data Index: 5632400 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1763. Min Range: -6.1763
Max Act: 5.9888. Min Act: -0.1700
Data Index: 921174 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1763. Min Range: -6.1763
Max Act: 6.0200. Min Act: -0.1700
Data Index: 783160 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1763. Min Range: -6.1763
Max Act: 5.9575. Min Act: -0.1700
Data Index: 5115330 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1763. Min Range: -6.1763
Max Act: 5.9575. Min Act: -0.1700
Data Index: 4335766 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1763. Min Range: -6.1763
Max Act: 5.9575. Min Act: -0.1700
Data Index: 2074685 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1763. Min Range: -6.1763
Max Act: 5.9575. Min Act: -0.1700
Data Index: 955357 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1763. Min Range: -6.1763
Max Act: 5.9575. Min Act: -0.1700
Data Index: 1656937 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1763. Min Range: -6.1763
Max Act: 5.9575. Min Act: -0.1700
Data Index: 8118292 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1763. Min Range: -6.1763
Max Act: 5.9575. Min Act: -0.1700
Data Index: 7868564 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1763. Min Range: -6.1763
Max Act: 5.9263. Min Act: -0.1700
Data Index: 1883625 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1763. Min Range: -6.1763
Max Act: 5.9263. Min Act: -0.1700
Data Index: 979232 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1763. Min Range: -6.1763
Max Act: 5.9575. Min Act: -0.1700
Data Index: 4001129 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1763. Min Range: -6.1763
Max Act: 5.9263. Min Act: -0.1700
Data Index: 2141509 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1763. Min Range: -6.1763
Max Act: 5.9263. Min Act: -0.1700
Data Index: 4322887 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1763. Min Range: -6.1763
Max Act: 5.9263. Min Act: -0.1700
Data Index: 1141208 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1763. Min Range: -6.1763
Max Act: 5.9263. Min Act: -0.1700
Data Index: 4971619 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1763. Min Range: -6.1763
Max Act: 5.9263. Min Act: -0.1700
Data Index: 409319 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19