Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 834 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.9274. Min Act: -0.1700
Data Index: 1218668 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.8024. Min Act: -0.1700
Data Index: 4883141 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.7712. Min Act: -0.1700
Data Index: 529212 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.7399. Min Act: -0.1700
Data Index: 6274602 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.7087. Min Act: -0.1700
Data Index: 122002 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.7087. Min Act: -0.1700
Data Index: 6938380 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.6774. Min Act: -0.1700
Data Index: 5403062 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.6774. Min Act: -0.1700
Data Index: 782257 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.7087. Min Act: -0.1700
Data Index: 1232078 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.6774. Min Act: -0.1700
Data Index: 3923832 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.6462. Min Act: -0.1700
Data Index: 6754806 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.6462. Min Act: -0.1700
Data Index: 8453603 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.6462. Min Act: -0.1700
Data Index: 1020379 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.6149. Min Act: -0.1700
Data Index: 6548668 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.6149. Min Act: -0.1700
Data Index: 3651868 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.6149. Min Act: -0.1700
Data Index: 8161628 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.5837. Min Act: -0.1700
Data Index: 8352872 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.6149. Min Act: -0.1700
Data Index: 6673320 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.5837. Min Act: -0.1700
Data Index: 5541559 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9274. Min Range: -5.9274
Max Act: 5.5837. Min Act: -0.1700
Data Index: 257129 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #19