Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5925 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8183. Min Range: -3.8183
Max Act: 3.8183. Min Act: -0.1700
Data Index: 8467986 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8183. Min Range: -3.8183
Max Act: 3.7401. Min Act: -0.1700
Data Index: 872580 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8183. Min Range: -3.8183
Max Act: 3.7245. Min Act: -0.1700
Data Index: 8162900 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8183. Min Range: -3.8183
Max Act: 3.7088. Min Act: -0.1700
Data Index: 3597199 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8183. Min Range: -3.8183
Max Act: 3.6463. Min Act: -0.1700
Data Index: 4779823 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8183. Min Range: -3.8183
Max Act: 3.5993. Min Act: -0.1700
Data Index: 3004271 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8183. Min Range: -3.8183
Max Act: 3.5837. Min Act: -0.1700
Data Index: 460207 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8183. Min Range: -3.8183
Max Act: 3.5680. Min Act: -0.1700
Data Index: 3283381 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8183. Min Range: -3.8183
Max Act: 3.5680. Min Act: -0.1700
Data Index: 4537533 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8183. Min Range: -3.8183
Max Act: 3.5210. Min Act: -0.1700
Data Index: 7528565 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8183. Min Range: -3.8183
Max Act: 3.5054. Min Act: -0.1700
Data Index: 8175565 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8183. Min Range: -3.8183
Max Act: 3.5210. Min Act: -0.1700
Data Index: 6152324 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8183. Min Range: -3.8183
Max Act: 3.5054. Min Act: -0.1700
Data Index: 4592255 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8183. Min Range: -3.8183
Max Act: 3.4897. Min Act: -0.1700
Data Index: 6133729 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8183. Min Range: -3.8183
Max Act: 3.4740. Min Act: -0.1700
Data Index: 5511036 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8183. Min Range: -3.8183
Max Act: 3.4740. Min Act: -0.1700
Data Index: 4421881 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8183. Min Range: -3.8183
Max Act: 3.4270. Min Act: -0.1700
Data Index: 8302048 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8183. Min Range: -3.8183
Max Act: 3.4427. Min Act: -0.1700
Data Index: 4714211 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8183. Min Range: -3.8183
Max Act: 3.4114. Min Act: -0.1700
Data Index: 30102 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8183. Min Range: -3.8183
Max Act: 3.4427. Min Act: -0.1700
Data Index: 7736565 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19