Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3796 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2651. Min Range: -7.2651
Max Act: 7.2651. Min Act: -0.1700
Data Index: 4755025 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2651. Min Range: -7.2651
Max Act: 6.9526. Min Act: -0.1700
Data Index: 4134625 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2651. Min Range: -7.2651
Max Act: 6.9526. Min Act: -0.1700
Data Index: 5139270 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2651. Min Range: -7.2651
Max Act: 6.8901. Min Act: -0.1700
Data Index: 1147274 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2651. Min Range: -7.2651
Max Act: 6.8276. Min Act: -0.1700
Data Index: 7932465 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2651. Min Range: -7.2651
Max Act: 6.7026. Min Act: -0.1700
Data Index: 4345819 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2651. Min Range: -7.2651
Max Act: 6.6713. Min Act: -0.1700
Data Index: 90497 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2651. Min Range: -7.2651
Max Act: 6.6401. Min Act: -0.1700
Data Index: 710720 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2651. Min Range: -7.2651
Max Act: 6.6713. Min Act: -0.1700
Data Index: 6600151 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2651. Min Range: -7.2651
Max Act: 6.6088. Min Act: -0.1700
Data Index: 6128634 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2651. Min Range: -7.2651
Max Act: 6.5776. Min Act: -0.1700
Data Index: 8648770 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2651. Min Range: -7.2651
Max Act: 6.5776. Min Act: -0.1700
Data Index: 1620681 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2651. Min Range: -7.2651
Max Act: 6.5776. Min Act: -0.1700
Data Index: 485960 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2651. Min Range: -7.2651
Max Act: 6.5463. Min Act: -0.1700
Data Index: 8327685 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2651. Min Range: -7.2651
Max Act: 6.5463. Min Act: -0.1700
Data Index: 8367151 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2651. Min Range: -7.2651
Max Act: 6.5151. Min Act: -0.1700
Data Index: 1271762 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2651. Min Range: -7.2651
Max Act: 6.5151. Min Act: -0.1700
Data Index: 7957742 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2651. Min Range: -7.2651
Max Act: 6.5151. Min Act: -0.1700
Data Index: 7742923 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2651. Min Range: -7.2651
Max Act: 6.5151. Min Act: -0.1700
Data Index: 6499361 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2651. Min Range: -7.2651
Max Act: 6.5151. Min Act: -0.1700
Data Index: 2317944 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19