Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3231 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1310. Min Range: -5.1310
Max Act: 5.1310. Min Act: -0.1700
Data Index: 8479354 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1310. Min Range: -5.1310
Max Act: 5.0685. Min Act: -0.1700
Data Index: 1382180 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1310. Min Range: -5.1310
Max Act: 5.0060. Min Act: -0.1700
Data Index: 1685064 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1310. Min Range: -5.1310
Max Act: 5.0685. Min Act: -0.1700
Data Index: 8458726 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1310. Min Range: -5.1310
Max Act: 5.0372. Min Act: -0.1700
Data Index: 4535874 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1310. Min Range: -5.1310
Max Act: 5.0372. Min Act: -0.1700
Data Index: 3274948 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1310. Min Range: -5.1310
Max Act: 5.0060. Min Act: -0.1700
Data Index: 5966234 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1310. Min Range: -5.1310
Max Act: 5.0060. Min Act: -0.1700
Data Index: 3734161 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9747. Min Act: -0.1700
Data Index: 4897979 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9435. Min Act: -0.1700
Data Index: 4956453 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9747. Min Act: -0.1700
Data Index: 6725903 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9122. Min Act: -0.1700
Data Index: 4878250 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9122. Min Act: -0.1700
Data Index: 7475221 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8810. Min Act: -0.1700
Data Index: 728054 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8810. Min Act: -0.1700
Data Index: 1356680 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.9122. Min Act: -0.1700
Data Index: 5746166 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8497. Min Act: -0.1700
Data Index: 7203240 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8810. Min Act: -0.1700
Data Index: 2904329 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8497. Min Act: -0.1700
Data Index: 176098 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1310. Min Range: -5.1310
Max Act: 4.8810. Min Act: -0.1700
Data Index: 2428107 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19