Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2686 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9948. Min Range: -7.9948
Max Act: 7.9636. Min Act: -0.1700
Data Index: 7120747 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9948. Min Range: -7.9948
Max Act: 7.9948. Min Act: -0.1700
Data Index: 2135412 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9948. Min Range: -7.9948
Max Act: 7.8073. Min Act: -0.1700
Data Index: 7216392 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9948. Min Range: -7.9948
Max Act: 7.7136. Min Act: -0.1700
Data Index: 5636182 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9948. Min Range: -7.9948
Max Act: 7.5886. Min Act: -0.1700
Data Index: 4657720 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9948. Min Range: -7.9948
Max Act: 7.5886. Min Act: -0.1700
Data Index: 5598843 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9948. Min Range: -7.9948
Max Act: 7.5573. Min Act: -0.1700
Data Index: 495158 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9948. Min Range: -7.9948
Max Act: 7.5261. Min Act: -0.1700
Data Index: 7916273 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9948. Min Range: -7.9948
Max Act: 7.5261. Min Act: -0.1700
Data Index: 7339063 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9948. Min Range: -7.9948
Max Act: 7.4948. Min Act: -0.1700
Data Index: 5022065 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9948. Min Range: -7.9948
Max Act: 7.4948. Min Act: -0.1700
Data Index: 1646121 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9948. Min Range: -7.9948
Max Act: 7.4948. Min Act: -0.1700
Data Index: 6020682 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9948. Min Range: -7.9948
Max Act: 7.4323. Min Act: -0.1700
Data Index: 2269016 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9948. Min Range: -7.9948
Max Act: 7.4323. Min Act: -0.1700
Data Index: 2304992 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9948. Min Range: -7.9948
Max Act: 7.4011. Min Act: -0.1700
Data Index: 514892 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9948. Min Range: -7.9948
Max Act: 7.4011. Min Act: -0.1700
Data Index: 1922679 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9948. Min Range: -7.9948
Max Act: 7.3698. Min Act: -0.1700
Data Index: 5110521 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9948. Min Range: -7.9948
Max Act: 7.3698. Min Act: -0.1700
Data Index: 29292 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9948. Min Range: -7.9948
Max Act: 7.3386. Min Act: -0.1700
Data Index: 5309089 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9948. Min Range: -7.9948
Max Act: 7.3386. Min Act: -0.1700
Data Index: 4094005 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19