Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4112 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8231. Min Range: -2.8231
Max Act: 2.8231. Min Act: -0.1700
Data Index: 571759 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8231. Min Range: -2.8231
Max Act: 2.7594. Min Act: -0.1700
Data Index: 5042342 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8231. Min Range: -2.8231
Max Act: 2.7114. Min Act: -0.1700
Data Index: 5827352 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8231. Min Range: -2.8231
Max Act: 2.6794. Min Act: -0.1700
Data Index: 7905343 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8231. Min Range: -2.8231
Max Act: 2.6634. Min Act: -0.1700
Data Index: 909527 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8231. Min Range: -2.8231
Max Act: 2.6313. Min Act: -0.1700
Data Index: 4191739 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8231. Min Range: -2.8231
Max Act: 2.6474. Min Act: -0.1700
Data Index: 2235877 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8231. Min Range: -2.8231
Max Act: 2.6152. Min Act: -0.1700
Data Index: 4946975 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8231. Min Range: -2.8231
Max Act: 2.6152. Min Act: -0.1700
Data Index: 5378935 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8231. Min Range: -2.8231
Max Act: 2.5669. Min Act: -0.1700
Data Index: 1912318 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8231. Min Range: -2.8231
Max Act: 2.5669. Min Act: -0.1700
Data Index: 8182411 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8231. Min Range: -2.8231
Max Act: 2.5669. Min Act: -0.1700
Data Index: 6785888 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8231. Min Range: -2.8231
Max Act: 2.5669. Min Act: -0.1700
Data Index: 5667685 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8231. Min Range: -2.8231
Max Act: 2.5508. Min Act: -0.1700
Data Index: 8132582 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8231. Min Range: -2.8231
Max Act: 2.5508. Min Act: -0.1700
Data Index: 4041455 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8231. Min Range: -2.8231
Max Act: 2.5508. Min Act: -0.1700
Data Index: 5479066 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8231. Min Range: -2.8231
Max Act: 2.5669. Min Act: -0.1700
Data Index: 1100838 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8231. Min Range: -2.8231
Max Act: 2.5346. Min Act: -0.1700
Data Index: 5079254 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8231. Min Range: -2.8231
Max Act: 2.5669. Min Act: -0.1700
Data Index: 4207586 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8231. Min Range: -2.8231
Max Act: 2.5508. Min Act: -0.1700
Data Index: 7723331 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19