Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9531. Min Range: -5.9531
Max Act: 5.9531. Min Act: -0.1700
Data Index: 1586481 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9531. Min Range: -5.9531
Max Act: 5.9219. Min Act: -0.1700
Data Index: 7626651 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9531. Min Range: -5.9531
Max Act: 5.8594. Min Act: -0.1700
Data Index: 7564182 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9531. Min Range: -5.9531
Max Act: 5.8594. Min Act: -0.1700
Data Index: 7264247 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9531. Min Range: -5.9531
Max Act: 5.8594. Min Act: -0.1700
Data Index: 3076257 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9531. Min Range: -5.9531
Max Act: 5.7969. Min Act: -0.1699
Data Index: 1022000 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9531. Min Range: -5.9531
Max Act: 5.8281. Min Act: -0.1700
Data Index: 3352659 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9531. Min Range: -5.9531
Max Act: 5.8281. Min Act: -0.1700
Data Index: 6336925 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9531. Min Range: -5.9531
Max Act: 5.8281. Min Act: -0.1700
Data Index: 4712606 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9531. Min Range: -5.9531
Max Act: 5.8281. Min Act: -0.1700
Data Index: 4338466 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9531. Min Range: -5.9531
Max Act: 5.8594. Min Act: -0.1700
Data Index: 4321200 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9531. Min Range: -5.9531
Max Act: 5.7969. Min Act: -0.1700
Data Index: 4256367 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9531. Min Range: -5.9531
Max Act: 5.8281. Min Act: -0.1700
Data Index: 4006124 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9531. Min Range: -5.9531
Max Act: 5.7656. Min Act: -0.1700
Data Index: 2693147 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9531. Min Range: -5.9531
Max Act: 5.7969. Min Act: -0.1699
Data Index: 4894541 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9531. Min Range: -5.9531
Max Act: 5.7969. Min Act: -0.1700
Data Index: 5355199 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9531. Min Range: -5.9531
Max Act: 5.7969. Min Act: -0.1700
Data Index: 5512316 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9531. Min Range: -5.9531
Max Act: 5.7969. Min Act: -0.1700
Data Index: 1150293 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9531. Min Range: -5.9531
Max Act: 5.7969. Min Act: -0.1700
Data Index: 8152040 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9531. Min Range: -5.9531
Max Act: 5.7969. Min Act: -0.1700
Data Index: 3666420 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19