Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1723 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.8302. Min Act: -0.1700
Data Index: 954203 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.7677. Min Act: -0.1700
Data Index: 2384246 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.7052. Min Act: -0.1700
Data Index: 302939 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.7052. Min Act: -0.1700
Data Index: 7906765 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.6114. Min Act: -0.1700
Data Index: 8173582 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.6114. Min Act: -0.1700
Data Index: 919262 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.6427. Min Act: -0.1700
Data Index: 7657806 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.5802. Min Act: -0.1700
Data Index: 5241475 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.6427. Min Act: -0.1700
Data Index: 1224337 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.5802. Min Act: -0.1700
Data Index: 3245516 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.5802. Min Act: -0.1700
Data Index: 6476989 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.5802. Min Act: -0.1700
Data Index: 2846789 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.5489. Min Act: -0.1700
Data Index: 2279517 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.5177. Min Act: -0.1700
Data Index: 1836518 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.5177. Min Act: -0.1700
Data Index: 6200579 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.5489. Min Act: -0.1700
Data Index: 6202254 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.5177. Min Act: -0.1700
Data Index: 5633406 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.4864. Min Act: -0.1700
Data Index: 631846 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.5177. Min Act: -0.1700
Data Index: 4101245 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8302. Min Range: -5.8302
Max Act: 5.5177. Min Act: -0.1700
Data Index: 5172214 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19