Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3675 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5205. Min Range: -9.5205
Max Act: 9.5205. Min Act: -0.1700
Data Index: 1307943 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5205. Min Range: -9.5205
Max Act: 9.2705. Min Act: -0.1700
Data Index: 104429 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5205. Min Range: -9.5205
Max Act: 8.9580. Min Act: -0.1700
Data Index: 6843043 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5205. Min Range: -9.5205
Max Act: 8.9580. Min Act: -0.1700
Data Index: 8560203 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5205. Min Range: -9.5205
Max Act: 8.8330. Min Act: -0.1700
Data Index: 5052627 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5205. Min Range: -9.5205
Max Act: 8.8955. Min Act: -0.1700
Data Index: 7827547 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5205. Min Range: -9.5205
Max Act: 8.8330. Min Act: -0.1700
Data Index: 6008879 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5205. Min Range: -9.5205
Max Act: 8.8955. Min Act: -0.1700
Data Index: 8560204 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5205. Min Range: -9.5205
Max Act: 8.8330. Min Act: -0.1700
Data Index: 6815580 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5205. Min Range: -9.5205
Max Act: 8.8330. Min Act: -0.1700
Data Index: 4521473 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5205. Min Range: -9.5205
Max Act: 8.7705. Min Act: -0.1700
Data Index: 375665 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5205. Min Range: -9.5205
Max Act: 8.8330. Min Act: -0.1700
Data Index: 6351469 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5205. Min Range: -9.5205
Max Act: 8.7705. Min Act: -0.1700
Data Index: 7878315 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5205. Min Range: -9.5205
Max Act: 8.7080. Min Act: -0.1700
Data Index: 3427169 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5205. Min Range: -9.5205
Max Act: 8.8330. Min Act: -0.1700
Data Index: 316409 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5205. Min Range: -9.5205
Max Act: 8.7705. Min Act: -0.1700
Data Index: 4385430 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5205. Min Range: -9.5205
Max Act: 8.7705. Min Act: -0.1700
Data Index: 7566921 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5205. Min Range: -9.5205
Max Act: 8.7705. Min Act: -0.1700
Data Index: 2958107 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5205. Min Range: -9.5205
Max Act: 8.7705. Min Act: -0.1700
Data Index: 4089143 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5205. Min Range: -9.5205
Max Act: 8.7080. Min Act: -0.1700
Data Index: 5998494 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19