Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5589 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9538. Min Range: -6.9538
Max Act: 6.9538. Min Act: -0.1700
Data Index: 4024266 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9538. Min Range: -6.9538
Max Act: 6.9225. Min Act: -0.1700
Data Index: 1592082 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9538. Min Range: -6.9538
Max Act: 6.9225. Min Act: -0.1700
Data Index: 4440826 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9538. Min Range: -6.9538
Max Act: 6.8288. Min Act: -0.1700
Data Index: 7172707 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9538. Min Range: -6.9538
Max Act: 6.7975. Min Act: -0.1700
Data Index: 5492819 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9538. Min Range: -6.9538
Max Act: 6.7975. Min Act: -0.1700
Data Index: 5338558 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9538. Min Range: -6.9538
Max Act: 6.7663. Min Act: -0.1700
Data Index: 476413 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9538. Min Range: -6.9538
Max Act: 6.7663. Min Act: -0.1700
Data Index: 3200899 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9538. Min Range: -6.9538
Max Act: 6.7038. Min Act: -0.1700
Data Index: 1796752 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9538. Min Range: -6.9538
Max Act: 6.7038. Min Act: -0.1700
Data Index: 996582 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9538. Min Range: -6.9538
Max Act: 6.7350. Min Act: -0.1700
Data Index: 8755347 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9538. Min Range: -6.9538
Max Act: 6.6725. Min Act: -0.1700
Data Index: 4941025 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9538. Min Range: -6.9538
Max Act: 6.6725. Min Act: -0.1700
Data Index: 8611028 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9538. Min Range: -6.9538
Max Act: 6.6413. Min Act: -0.1700
Data Index: 8699890 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9538. Min Range: -6.9538
Max Act: 6.6413. Min Act: -0.1700
Data Index: 1881191 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9538. Min Range: -6.9538
Max Act: 6.6100. Min Act: -0.1700
Data Index: 556735 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9538. Min Range: -6.9538
Max Act: 6.5475. Min Act: -0.1700
Data Index: 2263362 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9538. Min Range: -6.9538
Max Act: 6.5788. Min Act: -0.1700
Data Index: 7107976 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9538. Min Range: -6.9538
Max Act: 6.5163. Min Act: -0.1700
Data Index: 5535362 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9538. Min Range: -6.9538
Max Act: 6.5163. Min Act: -0.1700
Data Index: 3839155 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19