Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 58 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.4593. Min Act: -0.1700
Data Index: 3838205 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.3968. Min Act: -0.1700
Data Index: 6296197 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.3343. Min Act: -0.1700
Data Index: 745235 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.3030. Min Act: -0.1700
Data Index: 6865181 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.3030. Min Act: -0.1700
Data Index: 2525494 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.3030. Min Act: -0.1700
Data Index: 6665064 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.3030. Min Act: -0.1700
Data Index: 5907789 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.2718. Min Act: -0.1700
Data Index: 1181200 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.2718. Min Act: -0.1700
Data Index: 400239 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.2405. Min Act: -0.1700
Data Index: 185674 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.2405. Min Act: -0.1700
Data Index: 5642349 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.2093. Min Act: -0.1700
Data Index: 5543343 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.2093. Min Act: -0.1700
Data Index: 2330746 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.2093. Min Act: -0.1700
Data Index: 3150947 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.2093. Min Act: -0.1700
Data Index: 3594090 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.2093. Min Act: -0.1700
Data Index: 4538615 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.2093. Min Act: -0.1700
Data Index: 396222 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.1780. Min Act: -0.1700
Data Index: 5813468 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.1780. Min Act: -0.1700
Data Index: 2083394 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4593. Min Range: -5.4593
Max Act: 5.2093. Min Act: -0.1700
Data Index: 1137277 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19