Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1612 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6884. Min Range: -8.6884
Max Act: 8.6884. Min Act: -0.1700
Data Index: 1451363 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6884. Min Range: -8.6884
Max Act: 7.8759. Min Act: -0.1700
Data Index: 7746970 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6884. Min Range: -8.6884
Max Act: 7.6571. Min Act: -0.1700
Data Index: 4551177 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6884. Min Range: -8.6884
Max Act: 7.6571. Min Act: -0.1700
Data Index: 8520665 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6884. Min Range: -8.6884
Max Act: 7.6259. Min Act: -0.1700
Data Index: 5884420 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6884. Min Range: -8.6884
Max Act: 7.5946. Min Act: -0.1700
Data Index: 5649327 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6884. Min Range: -8.6884
Max Act: 7.5321. Min Act: -0.1700
Data Index: 4388335 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6884. Min Range: -8.6884
Max Act: 7.5321. Min Act: -0.1700
Data Index: 1245598 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6884. Min Range: -8.6884
Max Act: 7.4696. Min Act: -0.1700
Data Index: 7421301 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6884. Min Range: -8.6884
Max Act: 7.4696. Min Act: -0.1700
Data Index: 3132356 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6884. Min Range: -8.6884
Max Act: 7.4384. Min Act: -0.1700
Data Index: 5379094 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6884. Min Range: -8.6884
Max Act: 7.4384. Min Act: -0.1700
Data Index: 6404161 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6884. Min Range: -8.6884
Max Act: 7.4071. Min Act: -0.1700
Data Index: 1656526 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6884. Min Range: -8.6884
Max Act: 7.4071. Min Act: -0.1700
Data Index: 6540432 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6884. Min Range: -8.6884
Max Act: 7.3759. Min Act: -0.1700
Data Index: 5293607 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6884. Min Range: -8.6884
Max Act: 7.3759. Min Act: -0.1700
Data Index: 5864621 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6884. Min Range: -8.6884
Max Act: 7.3134. Min Act: -0.1700
Data Index: 2485146 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6884. Min Range: -8.6884
Max Act: 7.3134. Min Act: -0.1700
Data Index: 7310910 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6884. Min Range: -8.6884
Max Act: 7.3446. Min Act: -0.1700
Data Index: 5750673 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6884. Min Range: -8.6884
Max Act: 7.3134. Min Act: -0.1700
Data Index: 5529302 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #19