Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1334 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4247. Min Range: -6.4247
Max Act: 6.4247. Min Act: -0.1700
Data Index: 2695001 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4247. Min Range: -6.4247
Max Act: 6.2685. Min Act: -0.1700
Data Index: 8576824 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4247. Min Range: -6.4247
Max Act: 6.1435. Min Act: -0.1700
Data Index: 3379632 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4247. Min Range: -6.4247
Max Act: 6.1122. Min Act: -0.1700
Data Index: 4367272 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4247. Min Range: -6.4247
Max Act: 6.1122. Min Act: -0.1700
Data Index: 5943954 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4247. Min Range: -6.4247
Max Act: 6.0185. Min Act: -0.1700
Data Index: 3988236 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4247. Min Range: -6.4247
Max Act: 5.9872. Min Act: -0.1700
Data Index: 6134595 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4247. Min Range: -6.4247
Max Act: 5.9872. Min Act: -0.1700
Data Index: 7485461 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4247. Min Range: -6.4247
Max Act: 5.9247. Min Act: -0.1700
Data Index: 3043604 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4247. Min Range: -6.4247
Max Act: 5.9247. Min Act: -0.1700
Data Index: 7905390 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4247. Min Range: -6.4247
Max Act: 5.8622. Min Act: -0.1700
Data Index: 327889 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4247. Min Range: -6.4247
Max Act: 5.8622. Min Act: -0.1700
Data Index: 1288748 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4247. Min Range: -6.4247
Max Act: 5.8310. Min Act: -0.1700
Data Index: 4602424 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4247. Min Range: -6.4247
Max Act: 5.8310. Min Act: -0.1700
Data Index: 5589244 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4247. Min Range: -6.4247
Max Act: 5.7685. Min Act: -0.1700
Data Index: 39593 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4247. Min Range: -6.4247
Max Act: 5.7685. Min Act: -0.1700
Data Index: 112824 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4247. Min Range: -6.4247
Max Act: 5.7372. Min Act: -0.1700
Data Index: 7402889 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4247. Min Range: -6.4247
Max Act: 5.7060. Min Act: -0.1700
Data Index: 5050229 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4247. Min Range: -6.4247
Max Act: 5.7060. Min Act: -0.1700
Data Index: 6602621 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4247. Min Range: -6.4247
Max Act: 5.6747. Min Act: -0.1700
Data Index: 4371390 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19