Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2214 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3030. Min Range: -4.3030
Max Act: 4.3030. Min Act: -0.1700
Data Index: 7135787 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3030. Min Range: -4.3030
Max Act: 4.2717. Min Act: -0.1700
Data Index: 5376791 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3030. Min Range: -4.3030
Max Act: 4.1780. Min Act: -0.1700
Data Index: 4398738 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3030. Min Range: -4.3030
Max Act: 4.1154. Min Act: -0.1700
Data Index: 5771069 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3030. Min Range: -4.3030
Max Act: 4.0842. Min Act: -0.1700
Data Index: 219060 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3030. Min Range: -4.3030
Max Act: 4.0529. Min Act: -0.1700
Data Index: 337133 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3030. Min Range: -4.3030
Max Act: 4.0529. Min Act: -0.1700
Data Index: 337135 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3030. Min Range: -4.3030
Max Act: 4.0842. Min Act: -0.1700
Data Index: 337130 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3030. Min Range: -4.3030
Max Act: 4.0529. Min Act: -0.1700
Data Index: 337128 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3030. Min Range: -4.3030
Max Act: 4.0529. Min Act: -0.1700
Data Index: 369062 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3030. Min Range: -4.3030
Max Act: 4.0217. Min Act: -0.1700
Data Index: 2879102 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3030. Min Range: -4.3030
Max Act: 4.0217. Min Act: -0.1700
Data Index: 1444222 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3030. Min Range: -4.3030
Max Act: 3.9904. Min Act: -0.1700
Data Index: 8742738 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3030. Min Range: -4.3030
Max Act: 3.9904. Min Act: -0.1700
Data Index: 6639029 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3030. Min Range: -4.3030
Max Act: 3.9592. Min Act: -0.1700
Data Index: 244793 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3030. Min Range: -4.3030
Max Act: 3.9592. Min Act: -0.1700
Data Index: 3266338 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3030. Min Range: -4.3030
Max Act: 3.9592. Min Act: -0.1700
Data Index: 98778 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3030. Min Range: -4.3030
Max Act: 3.9592. Min Act: -0.1700
Data Index: 4554206 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3030. Min Range: -4.3030
Max Act: 3.9592. Min Act: -0.1700
Data Index: 1979411 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3030. Min Range: -4.3030
Max Act: 3.9279. Min Act: -0.1700
Data Index: 6550933 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19