Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2702 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7159. Min Range: -4.7159
Max Act: 4.7159. Min Act: -0.1700
Data Index: 8238120 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7159. Min Range: -4.7159
Max Act: 4.5909. Min Act: -0.1700
Data Index: 3260465 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7159. Min Range: -4.7159
Max Act: 4.6222. Min Act: -0.1700
Data Index: 6107384 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7159. Min Range: -4.7159
Max Act: 4.5597. Min Act: -0.1700
Data Index: 3421398 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7159. Min Range: -4.7159
Max Act: 4.4972. Min Act: -0.1700
Data Index: 1577235 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7159. Min Range: -4.7159
Max Act: 4.4972. Min Act: -0.1700
Data Index: 4649305 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7159. Min Range: -4.7159
Max Act: 4.4659. Min Act: -0.1700
Data Index: 1145200 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7159. Min Range: -4.7159
Max Act: 4.4659. Min Act: -0.1700
Data Index: 589464 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7159. Min Range: -4.7159
Max Act: 4.4659. Min Act: -0.1700
Data Index: 3562301 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7159. Min Range: -4.7159
Max Act: 4.4659. Min Act: -0.1700
Data Index: 8451520 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7159. Min Range: -4.7159
Max Act: 4.4347. Min Act: -0.1700
Data Index: 4685131 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7159. Min Range: -4.7159
Max Act: 4.4034. Min Act: -0.1700
Data Index: 2805511 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7159. Min Range: -4.7159
Max Act: 4.4034. Min Act: -0.1700
Data Index: 1037941 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7159. Min Range: -4.7159
Max Act: 4.4034. Min Act: -0.1700
Data Index: 7043215 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7159. Min Range: -4.7159
Max Act: 4.4034. Min Act: -0.1700
Data Index: 1409394 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7159. Min Range: -4.7159
Max Act: 4.4034. Min Act: -0.1700
Data Index: 4979099 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7159. Min Range: -4.7159
Max Act: 4.4034. Min Act: -0.1700
Data Index: 1409396 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7159. Min Range: -4.7159
Max Act: 4.4034. Min Act: -0.1700
Data Index: 3495974 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7159. Min Range: -4.7159
Max Act: 4.3722. Min Act: -0.1700
Data Index: 8008499 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7159. Min Range: -4.7159
Max Act: 4.3722. Min Act: -0.1700
Data Index: 6263282 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19