Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2768 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9543. Min Range: -6.9543
Max Act: 6.9543. Min Act: -0.1700
Data Index: 2516701 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9543. Min Range: -6.9543
Max Act: 6.8605. Min Act: -0.1700
Data Index: 3201482 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9543. Min Range: -6.9543
Max Act: 6.7668. Min Act: -0.1700
Data Index: 2250168 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9543. Min Range: -6.9543
Max Act: 6.7668. Min Act: -0.1700
Data Index: 7914305 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9543. Min Range: -6.9543
Max Act: 6.7355. Min Act: -0.1700
Data Index: 8441633 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9543. Min Range: -6.9543
Max Act: 6.7043. Min Act: -0.1700
Data Index: 1200922 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9543. Min Range: -6.9543
Max Act: 6.6105. Min Act: -0.1700
Data Index: 4043332 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9543. Min Range: -6.9543
Max Act: 6.5793. Min Act: -0.1700
Data Index: 4725955 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9543. Min Range: -6.9543
Max Act: 6.5168. Min Act: -0.1700
Data Index: 268772 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9543. Min Range: -6.9543
Max Act: 6.4855. Min Act: -0.1700
Data Index: 1082821 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9543. Min Range: -6.9543
Max Act: 6.4543. Min Act: -0.1700
Data Index: 2526367 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9543. Min Range: -6.9543
Max Act: 6.4543. Min Act: -0.1700
Data Index: 2244951 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9543. Min Range: -6.9543
Max Act: 6.4230. Min Act: -0.1700
Data Index: 2484840 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9543. Min Range: -6.9543
Max Act: 6.3918. Min Act: -0.1700
Data Index: 7985990 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9543. Min Range: -6.9543
Max Act: 6.4230. Min Act: -0.1700
Data Index: 4416066 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9543. Min Range: -6.9543
Max Act: 6.3918. Min Act: -0.1700
Data Index: 2198335 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9543. Min Range: -6.9543
Max Act: 6.3293. Min Act: -0.1700
Data Index: 5755802 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9543. Min Range: -6.9543
Max Act: 6.3293. Min Act: -0.1700
Data Index: 1598793 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9543. Min Range: -6.9543
Max Act: 6.2980. Min Act: -0.1700
Data Index: 2729958 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9543. Min Range: -6.9543
Max Act: 6.2980. Min Act: -0.1700
Data Index: 828867 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19