Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1958 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4274. Min Range: -8.4274
Max Act: 8.4274. Min Act: -0.1700
Data Index: 3089112 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4274. Min Range: -8.4274
Max Act: 8.1774. Min Act: -0.1700
Data Index: 305461 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4274. Min Range: -8.4274
Max Act: 7.9274. Min Act: -0.1700
Data Index: 7388011 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4274. Min Range: -8.4274
Max Act: 7.8337. Min Act: -0.1700
Data Index: 686184 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4274. Min Range: -8.4274
Max Act: 7.7087. Min Act: -0.1700
Data Index: 6778110 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4274. Min Range: -8.4274
Max Act: 7.7087. Min Act: -0.1700
Data Index: 7627213 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4274. Min Range: -8.4274
Max Act: 7.6149. Min Act: -0.1700
Data Index: 1135881 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4274. Min Range: -8.4274
Max Act: 7.6462. Min Act: -0.1700
Data Index: 7913528 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4274. Min Range: -8.4274
Max Act: 7.6149. Min Act: -0.1700
Data Index: 8472117 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4274. Min Range: -8.4274
Max Act: 7.5837. Min Act: -0.1700
Data Index: 6949443 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4274. Min Range: -8.4274
Max Act: 7.5837. Min Act: -0.1700
Data Index: 1083870 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4274. Min Range: -8.4274
Max Act: 7.6149. Min Act: -0.1700
Data Index: 7913518 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4274. Min Range: -8.4274
Max Act: 7.5837. Min Act: -0.1700
Data Index: 2017194 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4274. Min Range: -8.4274
Max Act: 7.5837. Min Act: -0.1700
Data Index: 8044199 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4274. Min Range: -8.4274
Max Act: 7.5524. Min Act: -0.1700
Data Index: 4126764 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4274. Min Range: -8.4274
Max Act: 7.4899. Min Act: -0.1700
Data Index: 2987624 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4274. Min Range: -8.4274
Max Act: 7.4587. Min Act: -0.1700
Data Index: 5755898 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4274. Min Range: -8.4274
Max Act: 7.4587. Min Act: -0.1700
Data Index: 5235840 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4274. Min Range: -8.4274
Max Act: 7.4274. Min Act: -0.1700
Data Index: 6564419 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4274. Min Range: -8.4274
Max Act: 7.3962. Min Act: -0.1700
Data Index: 976065 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19