Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3476 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8915. Min Range: -5.8915
Max Act: 5.8915. Min Act: -0.1700
Data Index: 4493624 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8915. Min Range: -5.8915
Max Act: 5.7665. Min Act: -0.1700
Data Index: 1328124 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8915. Min Range: -5.8915
Max Act: 5.7352. Min Act: -0.1700
Data Index: 917647 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8915. Min Range: -5.8915
Max Act: 5.6415. Min Act: -0.1700
Data Index: 7715211 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8915. Min Range: -5.8915
Max Act: 5.5790. Min Act: -0.1700
Data Index: 5127517 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8915. Min Range: -5.8915
Max Act: 5.5477. Min Act: -0.1700
Data Index: 7715209 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8915. Min Range: -5.8915
Max Act: 5.5477. Min Act: -0.1700
Data Index: 5664788 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8915. Min Range: -5.8915
Max Act: 5.5165. Min Act: -0.1700
Data Index: 7367439 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8915. Min Range: -5.8915
Max Act: 5.5165. Min Act: -0.1700
Data Index: 8306101 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8915. Min Range: -5.8915
Max Act: 5.4852. Min Act: -0.1699
Data Index: 7124454 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8915. Min Range: -5.8915
Max Act: 5.4540. Min Act: -0.1700
Data Index: 8320826 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8915. Min Range: -5.8915
Max Act: 5.4227. Min Act: -0.1700
Data Index: 3650745 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8915. Min Range: -5.8915
Max Act: 5.4227. Min Act: -0.1700
Data Index: 7795800 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8915. Min Range: -5.8915
Max Act: 5.4227. Min Act: -0.1700
Data Index: 3082247 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8915. Min Range: -5.8915
Max Act: 5.3915. Min Act: -0.1700
Data Index: 3438901 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8915. Min Range: -5.8915
Max Act: 5.3915. Min Act: -0.1700
Data Index: 1649820 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8915. Min Range: -5.8915
Max Act: 5.3915. Min Act: -0.1700
Data Index: 5084049 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8915. Min Range: -5.8915
Max Act: 5.3602. Min Act: -0.1700
Data Index: 4000837 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8915. Min Range: -5.8915
Max Act: 5.3290. Min Act: -0.1700
Data Index: 8724878 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8915. Min Range: -5.8915
Max Act: 5.3290. Min Act: -0.1700
Data Index: 5599690 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19