Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3443 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8337. Min Range: -8.8337
Max Act: 8.8337. Min Act: -0.1700
Data Index: 8583312 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8337. Min Range: -8.8337
Max Act: 8.8337. Min Act: -0.1700
Data Index: 2514679 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8337. Min Range: -8.8337
Max Act: 8.7087. Min Act: -0.1700
Data Index: 1614996 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8337. Min Range: -8.8337
Max Act: 8.7087. Min Act: -0.1700
Data Index: 4350275 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8337. Min Range: -8.8337
Max Act: 8.6462. Min Act: -0.1700
Data Index: 8348128 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8337. Min Range: -8.8337
Max Act: 8.6462. Min Act: -0.1700
Data Index: 8209839 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8337. Min Range: -8.8337
Max Act: 8.4587. Min Act: -0.1700
Data Index: 1902255 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8337. Min Range: -8.8337
Max Act: 8.4587. Min Act: -0.1700
Data Index: 3711248 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8337. Min Range: -8.8337
Max Act: 8.3337. Min Act: -0.1700
Data Index: 7357853 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8337. Min Range: -8.8337
Max Act: 8.3962. Min Act: -0.1700
Data Index: 1314301 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8337. Min Range: -8.8337
Max Act: 8.3962. Min Act: -0.1700
Data Index: 550491 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8337. Min Range: -8.8337
Max Act: 8.3962. Min Act: -0.1700
Data Index: 1305685 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8337. Min Range: -8.8337
Max Act: 8.3337. Min Act: -0.1700
Data Index: 7358197 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8337. Min Range: -8.8337
Max Act: 8.3337. Min Act: -0.1700
Data Index: 3744140 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8337. Min Range: -8.8337
Max Act: 8.3337. Min Act: -0.1700
Data Index: 6520027 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8337. Min Range: -8.8337
Max Act: 8.3337. Min Act: -0.1700
Data Index: 7128065 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8337. Min Range: -8.8337
Max Act: 8.2712. Min Act: -0.1699
Data Index: 1505476 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8337. Min Range: -8.8337
Max Act: 8.2712. Min Act: -0.1700
Data Index: 5141351 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8337. Min Range: -8.8337
Max Act: 8.2712. Min Act: -0.1700
Data Index: 7618032 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8337. Min Range: -8.8337
Max Act: 8.2712. Min Act: -0.1700
Data Index: 6284061 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19