Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4603 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0964. Min Range: -8.0964
Max Act: 8.0964. Min Act: -0.1700
Data Index: 883874 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0964. Min Range: -8.0964
Max Act: 8.0339. Min Act: -0.1700
Data Index: 4705930 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0964. Min Range: -8.0964
Max Act: 7.8464. Min Act: -0.1700
Data Index: 7225736 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0964. Min Range: -8.0964
Max Act: 7.7214. Min Act: -0.1700
Data Index: 5711529 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0964. Min Range: -8.0964
Max Act: 7.7214. Min Act: -0.1700
Data Index: 5641848 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0964. Min Range: -8.0964
Max Act: 7.5964. Min Act: -0.1700
Data Index: 4041006 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0964. Min Range: -8.0964
Max Act: 7.6589. Min Act: -0.1700
Data Index: 8746743 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0964. Min Range: -8.0964
Max Act: 7.5964. Min Act: -0.1700
Data Index: 3596033 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0964. Min Range: -8.0964
Max Act: 7.5964. Min Act: -0.1700
Data Index: 6089816 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0964. Min Range: -8.0964
Max Act: 7.5339. Min Act: -0.1700
Data Index: 4257729 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0964. Min Range: -8.0964
Max Act: 7.5339. Min Act: -0.1700
Data Index: 2854105 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0964. Min Range: -8.0964
Max Act: 7.4714. Min Act: -0.1700
Data Index: 6942688 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0964. Min Range: -8.0964
Max Act: 7.4714. Min Act: -0.1700
Data Index: 4276335 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0964. Min Range: -8.0964
Max Act: 7.4089. Min Act: -0.1700
Data Index: 58177 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0964. Min Range: -8.0964
Max Act: 7.4089. Min Act: -0.1700
Data Index: 2086119 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0964. Min Range: -8.0964
Max Act: 7.4089. Min Act: -0.1700
Data Index: 7530607 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0964. Min Range: -8.0964
Max Act: 7.3777. Min Act: -0.1700
Data Index: 7082995 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0964. Min Range: -8.0964
Max Act: 7.3777. Min Act: -0.1700
Data Index: 7905787 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0964. Min Range: -8.0964
Max Act: 7.3777. Min Act: -0.1700
Data Index: 2810999 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0964. Min Range: -8.0964
Max Act: 7.3464. Min Act: -0.1700
Data Index: 6798266 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #19