Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2897 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7450. Min Range: -9.7450
Max Act: 9.7450. Min Act: -0.1700
Data Index: 6851239 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7450. Min Range: -9.7450
Max Act: 9.4325. Min Act: -0.1700
Data Index: 6166224 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7450. Min Range: -9.7450
Max Act: 9.1200. Min Act: -0.1700
Data Index: 3315701 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7450. Min Range: -9.7450
Max Act: 9.0575. Min Act: -0.1700
Data Index: 1261674 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7450. Min Range: -9.7450
Max Act: 8.8700. Min Act: -0.1700
Data Index: 807865 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7450. Min Range: -9.7450
Max Act: 8.7450. Min Act: -0.1700
Data Index: 2537425 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7450. Min Range: -9.7450
Max Act: 8.6825. Min Act: -0.1700
Data Index: 3045708 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7450. Min Range: -9.7450
Max Act: 8.6200. Min Act: -0.1700
Data Index: 1540981 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7450. Min Range: -9.7450
Max Act: 8.5575. Min Act: -0.1700
Data Index: 8793268 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7450. Min Range: -9.7450
Max Act: 8.5575. Min Act: -0.1700
Data Index: 6892940 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7450. Min Range: -9.7450
Max Act: 8.3700. Min Act: -0.1700
Data Index: 2942531 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7450. Min Range: -9.7450
Max Act: 8.2762. Min Act: -0.1700
Data Index: 5878087 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7450. Min Range: -9.7450
Max Act: 8.2762. Min Act: -0.1700
Data Index: 958200 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7450. Min Range: -9.7450
Max Act: 8.2137. Min Act: -0.1700
Data Index: 5647154 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7450. Min Range: -9.7450
Max Act: 8.2450. Min Act: -0.1700
Data Index: 6399601 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7450. Min Range: -9.7450
Max Act: 8.1512. Min Act: -0.1700
Data Index: 7400988 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7450. Min Range: -9.7450
Max Act: 8.1200. Min Act: -0.1700
Data Index: 7959341 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7450. Min Range: -9.7450
Max Act: 8.1825. Min Act: -0.1700
Data Index: 6763556 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7450. Min Range: -9.7450
Max Act: 8.1512. Min Act: -0.1700
Data Index: 5755099 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7450. Min Range: -9.7450
Max Act: 8.1200. Min Act: -0.1700
Data Index: 3779826 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19