Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2798 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2248. Min Range: -3.2248
Max Act: 3.2248. Min Act: -0.1700
Data Index: 2240984 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2248. Min Range: -3.2248
Max Act: 3.1934. Min Act: -0.1700
Data Index: 6619286 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2248. Min Range: -3.2248
Max Act: 3.2091. Min Act: -0.1700
Data Index: 4460428 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2248. Min Range: -3.2248
Max Act: 3.1304. Min Act: -0.1700
Data Index: 118236 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2248. Min Range: -3.2248
Max Act: 3.1146. Min Act: -0.1700
Data Index: 7328137 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2248. Min Range: -3.2248
Max Act: 3.0989. Min Act: -0.1700
Data Index: 3839011 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2248. Min Range: -3.2248
Max Act: 3.1146. Min Act: -0.1700
Data Index: 3995719 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2248. Min Range: -3.2248
Max Act: 3.0831. Min Act: -0.1700
Data Index: 1641192 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2248. Min Range: -3.2248
Max Act: 3.0831. Min Act: -0.1700
Data Index: 6941377 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2248. Min Range: -3.2248
Max Act: 3.0516. Min Act: -0.1700
Data Index: 2520908 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2248. Min Range: -3.2248
Max Act: 3.0674. Min Act: -0.1700
Data Index: 691506 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2248. Min Range: -3.2248
Max Act: 3.0674. Min Act: -0.1700
Data Index: 2500392 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2248. Min Range: -3.2248
Max Act: 3.0200. Min Act: -0.1700
Data Index: 6887224 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2248. Min Range: -3.2248
Max Act: 3.0200. Min Act: -0.1700
Data Index: 683038 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2248. Min Range: -3.2248
Max Act: 3.0200. Min Act: -0.1700
Data Index: 3171160 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2248. Min Range: -3.2248
Max Act: 3.0200. Min Act: -0.1700
Data Index: 5528145 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2248. Min Range: -3.2248
Max Act: 3.0042. Min Act: -0.1700
Data Index: 5934641 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2248. Min Range: -3.2248
Max Act: 2.9884. Min Act: -0.1700
Data Index: 2326638 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2248. Min Range: -3.2248
Max Act: 2.9884. Min Act: -0.1700
Data Index: 7956797 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2248. Min Range: -3.2248
Max Act: 2.9884. Min Act: -0.1700
Data Index: 1611185 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19