Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 45 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0418. Min Range: -7.0418
Max Act: 7.0418. Min Act: -0.1700
Data Index: 1719829 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.5418. Min Act: -0.1700
Data Index: 6068503 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.5105. Min Act: -0.1700
Data Index: 4432006 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.3543. Min Act: -0.1700
Data Index: 2690074 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.3855. Min Act: -0.1700
Data Index: 2063693 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.3855. Min Act: -0.1700
Data Index: 5685783 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.3543. Min Act: -0.1700
Data Index: 4831357 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.3230. Min Act: -0.1700
Data Index: 1983284 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.2918. Min Act: -0.1700
Data Index: 4010696 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.3230. Min Act: -0.1700
Data Index: 3901167 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.2918. Min Act: -0.1700
Data Index: 8423105 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.2918. Min Act: -0.1700
Data Index: 3901166 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.2918. Min Act: -0.1700
Data Index: 2115071 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.2918. Min Act: -0.1700
Data Index: 6119188 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.2293. Min Act: -0.1700
Data Index: 7893674 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.2293. Min Act: -0.1700
Data Index: 1976887 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.1980. Min Act: -0.1700
Data Index: 2815696 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.2293. Min Act: -0.1700
Data Index: 4445948 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.1980. Min Act: -0.1700
Data Index: 4753761 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0418. Min Range: -7.0418
Max Act: 6.1668. Min Act: -0.1700
Data Index: 829473 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19