Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1151 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.0896. Min Range: -1.0896
Max Act: 1.0896. Min Act: -0.1700
Data Index: 7165260 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0896. Min Range: -1.0896
Max Act: 1.0372. Min Act: -0.1700
Data Index: 4181885 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0896. Min Range: -1.0896
Max Act: 1.0372. Min Act: -0.1700
Data Index: 5040396 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0896. Min Range: -1.0896
Max Act: 1.0372. Min Act: -0.1700
Data Index: 8524548 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0896. Min Range: -1.0896
Max Act: 1.0111. Min Act: -0.1700
Data Index: 5625778 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0896. Min Range: -1.0896
Max Act: 1.0024. Min Act: -0.1700
Data Index: 2901504 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0896. Min Range: -1.0896
Max Act: 1.0111. Min Act: -0.1700
Data Index: 5501323 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0896. Min Range: -1.0896
Max Act: 1.0024. Min Act: -0.1700
Data Index: 1649993 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0896. Min Range: -1.0896
Max Act: 1.0024. Min Act: -0.1700
Data Index: 3409482 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0896. Min Range: -1.0896
Max Act: 0.9937. Min Act: -0.1700
Data Index: 1247432 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0896. Min Range: -1.0896
Max Act: 1.0024. Min Act: -0.1700
Data Index: 7967931 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0896. Min Range: -1.0896
Max Act: 1.0024. Min Act: -0.1700
Data Index: 4376194 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0896. Min Range: -1.0896
Max Act: 1.0024. Min Act: -0.1700
Data Index: 133113 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0896. Min Range: -1.0896
Max Act: 0.9937. Min Act: -0.1700
Data Index: 7382919 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0896. Min Range: -1.0896
Max Act: 0.9937. Min Act: -0.1700
Data Index: 2955978 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0896. Min Range: -1.0896
Max Act: 0.9937. Min Act: -0.1700
Data Index: 5625933 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0896. Min Range: -1.0896
Max Act: 0.9850. Min Act: -0.1700
Data Index: 5965733 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0896. Min Range: -1.0896
Max Act: 0.9764. Min Act: -0.1700
Data Index: 5187533 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0896. Min Range: -1.0896
Max Act: 0.9937. Min Act: -0.1700
Data Index: 5662807 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0896. Min Range: -1.0896
Max Act: 0.9937. Min Act: -0.1700
Data Index: 6125144 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19