Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 998 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3295. Min Range: -5.3295
Max Act: 5.2357. Min Act: -0.1700
Data Index: 2801093 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3295. Min Range: -5.3295
Max Act: 5.3295. Min Act: -0.1700
Data Index: 5466953 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3295. Min Range: -5.3295
Max Act: 5.1107. Min Act: -0.1700
Data Index: 6845319 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3295. Min Range: -5.3295
Max Act: 5.0482. Min Act: -0.1700
Data Index: 7429271 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3295. Min Range: -5.3295
Max Act: 5.0795. Min Act: -0.1700
Data Index: 1252450 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3295. Min Range: -5.3295
Max Act: 4.9857. Min Act: -0.1700
Data Index: 5796464 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3295. Min Range: -5.3295
Max Act: 4.9857. Min Act: -0.1700
Data Index: 2102517 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3295. Min Range: -5.3295
Max Act: 4.9545. Min Act: -0.1700
Data Index: 6033609 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3295. Min Range: -5.3295
Max Act: 4.9857. Min Act: -0.1700
Data Index: 4631561 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3295. Min Range: -5.3295
Max Act: 4.9232. Min Act: -0.1700
Data Index: 8124618 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3295. Min Range: -5.3295
Max Act: 4.8607. Min Act: -0.1700
Data Index: 116632 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3295. Min Range: -5.3295
Max Act: 4.8920. Min Act: -0.1700
Data Index: 7474333 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3295. Min Range: -5.3295
Max Act: 4.8920. Min Act: -0.1700
Data Index: 7870670 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3295. Min Range: -5.3295
Max Act: 4.8607. Min Act: -0.1700
Data Index: 7322880 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3295. Min Range: -5.3295
Max Act: 4.8607. Min Act: -0.1700
Data Index: 8541622 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3295. Min Range: -5.3295
Max Act: 4.8295. Min Act: -0.1700
Data Index: 576056 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3295. Min Range: -5.3295
Max Act: 4.7982. Min Act: -0.1700
Data Index: 1728000 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3295. Min Range: -5.3295
Max Act: 4.7982. Min Act: -0.1700
Data Index: 3461104 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3295. Min Range: -5.3295
Max Act: 4.7670. Min Act: -0.1700
Data Index: 4687554 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3295. Min Range: -5.3295
Max Act: 4.7670. Min Act: -0.1700
Data Index: 1960187 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19