Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5429 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5168. Min Range: -7.5168
Max Act: 7.5168. Min Act: -0.1700
Data Index: 8272109 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5168. Min Range: -7.5168
Max Act: 7.4543. Min Act: -0.1700
Data Index: 1267106 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5168. Min Range: -7.5168
Max Act: 7.3918. Min Act: -0.1700
Data Index: 8781951 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5168. Min Range: -7.5168
Max Act: 7.3606. Min Act: -0.1700
Data Index: 3044359 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5168. Min Range: -7.5168
Max Act: 7.3293. Min Act: -0.1700
Data Index: 966639 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5168. Min Range: -7.5168
Max Act: 7.3293. Min Act: -0.1700
Data Index: 1226074 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5168. Min Range: -7.5168
Max Act: 7.2981. Min Act: -0.1700
Data Index: 5964775 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5168. Min Range: -7.5168
Max Act: 7.2668. Min Act: -0.1700
Data Index: 3715082 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5168. Min Range: -7.5168
Max Act: 7.2668. Min Act: -0.1700
Data Index: 5527103 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5168. Min Range: -7.5168
Max Act: 7.2356. Min Act: -0.1700
Data Index: 7322766 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5168. Min Range: -7.5168
Max Act: 7.2043. Min Act: -0.1700
Data Index: 8791149 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5168. Min Range: -7.5168
Max Act: 7.1731. Min Act: -0.1700
Data Index: 6010240 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5168. Min Range: -7.5168
Max Act: 7.2356. Min Act: -0.1700
Data Index: 686568 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5168. Min Range: -7.5168
Max Act: 7.2043. Min Act: -0.1700
Data Index: 4573725 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5168. Min Range: -7.5168
Max Act: 7.2043. Min Act: -0.1700
Data Index: 7989729 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5168. Min Range: -7.5168
Max Act: 7.2043. Min Act: -0.1700
Data Index: 5118281 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5168. Min Range: -7.5168
Max Act: 7.2043. Min Act: -0.1700
Data Index: 8622514 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5168. Min Range: -7.5168
Max Act: 7.1731. Min Act: -0.1700
Data Index: 754164 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5168. Min Range: -7.5168
Max Act: 7.2043. Min Act: -0.1700
Data Index: 8428 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5168. Min Range: -7.5168
Max Act: 7.1731. Min Act: -0.1700
Data Index: 3875886 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19