Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2893 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0381. Min Range: -7.0381
Max Act: 7.0381. Min Act: -0.1700
Data Index: 4650643 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0381. Min Range: -7.0381
Max Act: 6.7256. Min Act: -0.1700
Data Index: 5730502 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0381. Min Range: -7.0381
Max Act: 6.6943. Min Act: -0.1700
Data Index: 8506012 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0381. Min Range: -7.0381
Max Act: 6.6006. Min Act: -0.1700
Data Index: 7789016 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0381. Min Range: -7.0381
Max Act: 6.6006. Min Act: -0.1700
Data Index: 3838047 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0381. Min Range: -7.0381
Max Act: 6.4756. Min Act: -0.1700
Data Index: 8519745 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0381. Min Range: -7.0381
Max Act: 6.4756. Min Act: -0.1700
Data Index: 3545758 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0381. Min Range: -7.0381
Max Act: 6.4756. Min Act: -0.1700
Data Index: 7559228 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0381. Min Range: -7.0381
Max Act: 6.4443. Min Act: -0.1700
Data Index: 3453039 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0381. Min Range: -7.0381
Max Act: 6.3818. Min Act: -0.1700
Data Index: 8151210 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0381. Min Range: -7.0381
Max Act: 6.4131. Min Act: -0.1700
Data Index: 4338092 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0381. Min Range: -7.0381
Max Act: 6.4131. Min Act: -0.1700
Data Index: 12616 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0381. Min Range: -7.0381
Max Act: 6.3506. Min Act: -0.1700
Data Index: 4429859 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0381. Min Range: -7.0381
Max Act: 6.3818. Min Act: -0.1700
Data Index: 357231 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0381. Min Range: -7.0381
Max Act: 6.3506. Min Act: -0.1700
Data Index: 2496395 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0381. Min Range: -7.0381
Max Act: 6.3506. Min Act: -0.1700
Data Index: 1066529 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0381. Min Range: -7.0381
Max Act: 6.3506. Min Act: -0.1700
Data Index: 1452 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0381. Min Range: -7.0381
Max Act: 6.3818. Min Act: -0.1700
Data Index: 5455008 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0381. Min Range: -7.0381
Max Act: 6.3193. Min Act: -0.1700
Data Index: 5619352 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0381. Min Range: -7.0381
Max Act: 6.3193. Min Act: -0.1700
Data Index: 6980760 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19