Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2075 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0458. Min Range: -6.0458
Max Act: 6.0458. Min Act: -0.1700
Data Index: 2821389 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0458. Min Range: -6.0458
Max Act: 5.8583. Min Act: -0.1700
Data Index: 2396137 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0458. Min Range: -6.0458
Max Act: 5.8270. Min Act: -0.1700
Data Index: 441290 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0458. Min Range: -6.0458
Max Act: 5.8270. Min Act: -0.1700
Data Index: 2146123 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0458. Min Range: -6.0458
Max Act: 5.8270. Min Act: -0.1700
Data Index: 5991571 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0458. Min Range: -6.0458
Max Act: 5.7958. Min Act: -0.1700
Data Index: 1982929 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0458. Min Range: -6.0458
Max Act: 5.7333. Min Act: -0.1700
Data Index: 8593699 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0458. Min Range: -6.0458
Max Act: 5.7333. Min Act: -0.1700
Data Index: 8462422 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0458. Min Range: -6.0458
Max Act: 5.7333. Min Act: -0.1700
Data Index: 1976 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0458. Min Range: -6.0458
Max Act: 5.7020. Min Act: -0.1700
Data Index: 3761565 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0458. Min Range: -6.0458
Max Act: 5.6708. Min Act: -0.1700
Data Index: 1558619 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0458. Min Range: -6.0458
Max Act: 5.6395. Min Act: -0.1700
Data Index: 5507227 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0458. Min Range: -6.0458
Max Act: 5.6395. Min Act: -0.1700
Data Index: 8676958 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0458. Min Range: -6.0458
Max Act: 5.6083. Min Act: -0.1700
Data Index: 1558620 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0458. Min Range: -6.0458
Max Act: 5.5458. Min Act: -0.1700
Data Index: 8593700 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0458. Min Range: -6.0458
Max Act: 5.5770. Min Act: -0.1700
Data Index: 5984281 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0458. Min Range: -6.0458
Max Act: 5.5458. Min Act: -0.1700
Data Index: 4623675 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0458. Min Range: -6.0458
Max Act: 5.5145. Min Act: -0.1700
Data Index: 8597970 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0458. Min Range: -6.0458
Max Act: 5.5145. Min Act: -0.1700
Data Index: 5275229 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0458. Min Range: -6.0458
Max Act: 5.4520. Min Act: -0.1700
Data Index: 5984280 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19