Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4547 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9948. Min Range: -6.9948
Max Act: 6.9948. Min Act: -0.1700
Data Index: 1633706 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9948. Min Range: -6.9948
Max Act: 6.8386. Min Act: -0.1700
Data Index: 1819048 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9948. Min Range: -6.9948
Max Act: 6.7448. Min Act: -0.1700
Data Index: 3127070 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9948. Min Range: -6.9948
Max Act: 6.7136. Min Act: -0.1700
Data Index: 8544081 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9948. Min Range: -6.9948
Max Act: 6.6511. Min Act: -0.1700
Data Index: 1403258 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9948. Min Range: -6.9948
Max Act: 6.5886. Min Act: -0.1700
Data Index: 7708088 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9948. Min Range: -6.9948
Max Act: 6.5573. Min Act: -0.1700
Data Index: 6365848 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9948. Min Range: -6.9948
Max Act: 6.5573. Min Act: -0.1700
Data Index: 6473348 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9948. Min Range: -6.9948
Max Act: 6.5261. Min Act: -0.1700
Data Index: 8426587 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9948. Min Range: -6.9948
Max Act: 6.4323. Min Act: -0.1700
Data Index: 7657895 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9948. Min Range: -6.9948
Max Act: 6.4323. Min Act: -0.1700
Data Index: 2039889 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9948. Min Range: -6.9948
Max Act: 6.4323. Min Act: -0.1700
Data Index: 4968432 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9948. Min Range: -6.9948
Max Act: 6.4011. Min Act: -0.1700
Data Index: 1400539 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9948. Min Range: -6.9948
Max Act: 6.4011. Min Act: -0.1700
Data Index: 7369183 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9948. Min Range: -6.9948
Max Act: 6.4011. Min Act: -0.1700
Data Index: 4742334 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9948. Min Range: -6.9948
Max Act: 6.4011. Min Act: -0.1700
Data Index: 8126241 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9948. Min Range: -6.9948
Max Act: 6.3698. Min Act: -0.1700
Data Index: 4973727 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9948. Min Range: -6.9948
Max Act: 6.4011. Min Act: -0.1700
Data Index: 2513060 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9948. Min Range: -6.9948
Max Act: 6.3698. Min Act: -0.1700
Data Index: 5986482 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9948. Min Range: -6.9948
Max Act: 6.3698. Min Act: -0.1700
Data Index: 3524720 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19