Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2973 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8205. Min Range: -6.8205
Max Act: 6.8205. Min Act: -0.1700
Data Index: 6225059 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8205. Min Range: -6.8205
Max Act: 6.8205. Min Act: -0.1700
Data Index: 1578140 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8205. Min Range: -6.8205
Max Act: 6.7268. Min Act: -0.1700
Data Index: 6190407 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8205. Min Range: -6.8205
Max Act: 6.6330. Min Act: -0.1700
Data Index: 3352609 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8205. Min Range: -6.8205
Max Act: 6.6955. Min Act: -0.1700
Data Index: 4936799 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8205. Min Range: -6.8205
Max Act: 6.5705. Min Act: -0.1700
Data Index: 6167203 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8205. Min Range: -6.8205
Max Act: 6.5705. Min Act: -0.1700
Data Index: 4680314 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8205. Min Range: -6.8205
Max Act: 6.5080. Min Act: -0.1700
Data Index: 988075 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8205. Min Range: -6.8205
Max Act: 6.5080. Min Act: -0.1700
Data Index: 5423042 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8205. Min Range: -6.8205
Max Act: 6.5393. Min Act: -0.1700
Data Index: 3909469 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8205. Min Range: -6.8205
Max Act: 6.4455. Min Act: -0.1700
Data Index: 909424 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8205. Min Range: -6.8205
Max Act: 6.4455. Min Act: -0.1700
Data Index: 8139121 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8205. Min Range: -6.8205
Max Act: 6.4455. Min Act: -0.1700
Data Index: 549368 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8205. Min Range: -6.8205
Max Act: 6.4143. Min Act: -0.1700
Data Index: 1267819 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8205. Min Range: -6.8205
Max Act: 6.4143. Min Act: -0.1700
Data Index: 2799392 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8205. Min Range: -6.8205
Max Act: 6.4143. Min Act: -0.1700
Data Index: 1674195 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8205. Min Range: -6.8205
Max Act: 6.4143. Min Act: -0.1700
Data Index: 4082788 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8205. Min Range: -6.8205
Max Act: 6.4143. Min Act: -0.1700
Data Index: 7348304 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8205. Min Range: -6.8205
Max Act: 6.3518. Min Act: -0.1700
Data Index: 7315801 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8205. Min Range: -6.8205
Max Act: 6.4143. Min Act: -0.1700
Data Index: 2310911 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19