Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3436 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3005. Min Range: -5.3005
Max Act: 5.3005. Min Act: -0.1700
Data Index: 4329591 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3005. Min Range: -5.3005
Max Act: 5.2380. Min Act: -0.1700
Data Index: 4946677 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3005. Min Range: -5.3005
Max Act: 5.2380. Min Act: -0.1700
Data Index: 3537284 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3005. Min Range: -5.3005
Max Act: 5.2068. Min Act: -0.1700
Data Index: 8328249 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3005. Min Range: -5.3005
Max Act: 5.2068. Min Act: -0.1700
Data Index: 6889981 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3005. Min Range: -5.3005
Max Act: 5.1755. Min Act: -0.1700
Data Index: 1954384 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3005. Min Range: -5.3005
Max Act: 5.2068. Min Act: -0.1700
Data Index: 6266547 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3005. Min Range: -5.3005
Max Act: 5.1755. Min Act: -0.1700
Data Index: 1441061 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3005. Min Range: -5.3005
Max Act: 5.1443. Min Act: -0.1700
Data Index: 8060451 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3005. Min Range: -5.3005
Max Act: 5.1130. Min Act: -0.1700
Data Index: 504065 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3005. Min Range: -5.3005
Max Act: 5.1130. Min Act: -0.1700
Data Index: 1588666 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3005. Min Range: -5.3005
Max Act: 5.1130. Min Act: -0.1700
Data Index: 2638215 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3005. Min Range: -5.3005
Max Act: 5.0818. Min Act: -0.1700
Data Index: 6099973 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3005. Min Range: -5.3005
Max Act: 5.0818. Min Act: -0.1700
Data Index: 2066263 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3005. Min Range: -5.3005
Max Act: 5.0818. Min Act: -0.1700
Data Index: 5140783 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3005. Min Range: -5.3005
Max Act: 5.0818. Min Act: -0.1700
Data Index: 6180259 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3005. Min Range: -5.3005
Max Act: 5.0818. Min Act: -0.1700
Data Index: 5750564 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3005. Min Range: -5.3005
Max Act: 5.0505. Min Act: -0.1700
Data Index: 5420411 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3005. Min Range: -5.3005
Max Act: 5.0505. Min Act: -0.1700
Data Index: 2589079 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3005. Min Range: -5.3005
Max Act: 5.0505. Min Act: -0.1700
Data Index: 678273 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19