Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1008 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0118. Min Range: -7.0118
Max Act: 7.0118. Min Act: -0.1700
Data Index: 3624850 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0118. Min Range: -7.0118
Max Act: 6.9805. Min Act: -0.1700
Data Index: 2463826 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0118. Min Range: -7.0118
Max Act: 6.8555. Min Act: -0.1700
Data Index: 2692377 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0118. Min Range: -7.0118
Max Act: 6.8243. Min Act: -0.1700
Data Index: 2418318 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0118. Min Range: -7.0118
Max Act: 6.6993. Min Act: -0.1700
Data Index: 3302190 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0118. Min Range: -7.0118
Max Act: 6.6680. Min Act: -0.1700
Data Index: 2513327 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0118. Min Range: -7.0118
Max Act: 6.6368. Min Act: -0.1700
Data Index: 1833553 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0118. Min Range: -7.0118
Max Act: 6.6055. Min Act: -0.1700
Data Index: 3475777 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0118. Min Range: -7.0118
Max Act: 6.5430. Min Act: -0.1700
Data Index: 2585428 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0118. Min Range: -7.0118
Max Act: 6.5118. Min Act: -0.1700
Data Index: 8555929 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0118. Min Range: -7.0118
Max Act: 6.5743. Min Act: -0.1700
Data Index: 1107012 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0118. Min Range: -7.0118
Max Act: 6.5430. Min Act: -0.1700
Data Index: 2380991 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0118. Min Range: -7.0118
Max Act: 6.5430. Min Act: -0.1700
Data Index: 7124121 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0118. Min Range: -7.0118
Max Act: 6.5118. Min Act: -0.1700
Data Index: 1869308 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0118. Min Range: -7.0118
Max Act: 6.5118. Min Act: -0.1700
Data Index: 5401492 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0118. Min Range: -7.0118
Max Act: 6.5118. Min Act: -0.1700
Data Index: 4991275 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0118. Min Range: -7.0118
Max Act: 6.5430. Min Act: -0.1700
Data Index: 147939 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0118. Min Range: -7.0118
Max Act: 6.4805. Min Act: -0.1700
Data Index: 2461958 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0118. Min Range: -7.0118
Max Act: 6.4805. Min Act: -0.1700
Data Index: 3153248 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0118. Min Range: -7.0118
Max Act: 6.5118. Min Act: -0.1700
Data Index: 6416210 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19