Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2977 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6137. Min Range: -3.6137
Max Act: 3.6137. Min Act: -0.1700
Data Index: 2676456 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6137. Min Range: -3.6137
Max Act: 3.5511. Min Act: -0.1700
Data Index: 6564696 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6137. Min Range: -3.6137
Max Act: 3.4728. Min Act: -0.1700
Data Index: 8477262 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6137. Min Range: -3.6137
Max Act: 3.4571. Min Act: -0.1700
Data Index: 5200125 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6137. Min Range: -3.6137
Max Act: 3.4414. Min Act: -0.1700
Data Index: 3428216 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6137. Min Range: -3.6137
Max Act: 3.4101. Min Act: -0.1700
Data Index: 3347809 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6137. Min Range: -3.6137
Max Act: 3.3631. Min Act: -0.1700
Data Index: 6286356 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6137. Min Range: -3.6137
Max Act: 3.3631. Min Act: -0.1700
Data Index: 1825728 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6137. Min Range: -3.6137
Max Act: 3.3474. Min Act: -0.1700
Data Index: 1758643 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6137. Min Range: -3.6137
Max Act: 3.3317. Min Act: -0.1700
Data Index: 2218689 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6137. Min Range: -3.6137
Max Act: 3.3317. Min Act: -0.1700
Data Index: 5616367 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6137. Min Range: -3.6137
Max Act: 3.3317. Min Act: -0.1700
Data Index: 370041 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6137. Min Range: -3.6137
Max Act: 3.3160. Min Act: -0.1700
Data Index: 3176704 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6137. Min Range: -3.6137
Max Act: 3.3160. Min Act: -0.1700
Data Index: 7962741 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6137. Min Range: -3.6137
Max Act: 3.3003. Min Act: -0.1700
Data Index: 5597754 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6137. Min Range: -3.6137
Max Act: 3.3003. Min Act: -0.1700
Data Index: 7888648 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6137. Min Range: -3.6137
Max Act: 3.3003. Min Act: -0.1700
Data Index: 5707257 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6137. Min Range: -3.6137
Max Act: 3.3160. Min Act: -0.1700
Data Index: 3508194 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6137. Min Range: -3.6137
Max Act: 3.3003. Min Act: -0.1700
Data Index: 4607435 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6137. Min Range: -3.6137
Max Act: 3.2846. Min Act: -0.1700
Data Index: 2211284 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19