Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2590 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0515. Min Range: -6.0515
Max Act: 6.0515. Min Act: -0.1700
Data Index: 3231663 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0515. Min Range: -6.0515
Max Act: 5.8327. Min Act: -0.1700
Data Index: 7972897 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0515. Min Range: -6.0515
Max Act: 5.7390. Min Act: -0.1700
Data Index: 1018628 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0515. Min Range: -6.0515
Max Act: 5.6452. Min Act: -0.1700
Data Index: 771285 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0515. Min Range: -6.0515
Max Act: 5.5515. Min Act: -0.1700
Data Index: 2595353 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0515. Min Range: -6.0515
Max Act: 5.4890. Min Act: -0.1700
Data Index: 5476185 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0515. Min Range: -6.0515
Max Act: 5.4890. Min Act: -0.1700
Data Index: 7054288 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0515. Min Range: -6.0515
Max Act: 5.4890. Min Act: -0.1700
Data Index: 5870147 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0515. Min Range: -6.0515
Max Act: 5.4890. Min Act: -0.1700
Data Index: 274548 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0515. Min Range: -6.0515
Max Act: 5.4890. Min Act: -0.1700
Data Index: 399795 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0515. Min Range: -6.0515
Max Act: 5.4577. Min Act: -0.1700
Data Index: 7005319 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0515. Min Range: -6.0515
Max Act: 5.4577. Min Act: -0.1700
Data Index: 1257140 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0515. Min Range: -6.0515
Max Act: 5.4577. Min Act: -0.1700
Data Index: 1194370 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0515. Min Range: -6.0515
Max Act: 5.4577. Min Act: -0.1700
Data Index: 6217088 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0515. Min Range: -6.0515
Max Act: 5.4265. Min Act: -0.1700
Data Index: 3352369 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0515. Min Range: -6.0515
Max Act: 5.4265. Min Act: -0.1700
Data Index: 8480281 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0515. Min Range: -6.0515
Max Act: 5.4265. Min Act: -0.1700
Data Index: 8010670 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0515. Min Range: -6.0515
Max Act: 5.4265. Min Act: -0.1700
Data Index: 520747 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0515. Min Range: -6.0515
Max Act: 5.3952. Min Act: -0.1700
Data Index: 2732688 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0515. Min Range: -6.0515
Max Act: 5.3640. Min Act: -0.1700
Data Index: 6508532 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19