Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3210 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8200. Min Range: -4.8200
Max Act: 4.8200. Min Act: -0.1700
Data Index: 4072670 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8200. Min Range: -4.8200
Max Act: 4.7262. Min Act: -0.1700
Data Index: 241696 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8200. Min Range: -4.8200
Max Act: 4.6637. Min Act: -0.1700
Data Index: 1913832 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8200. Min Range: -4.8200
Max Act: 4.6325. Min Act: -0.1700
Data Index: 8201739 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8200. Min Range: -4.8200
Max Act: 4.6012. Min Act: -0.1700
Data Index: 4893911 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8200. Min Range: -4.8200
Max Act: 4.5387. Min Act: -0.1700
Data Index: 4320793 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8200. Min Range: -4.8200
Max Act: 4.5075. Min Act: -0.1700
Data Index: 2505311 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8200. Min Range: -4.8200
Max Act: 4.4450. Min Act: -0.1700
Data Index: 1414286 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8200. Min Range: -4.8200
Max Act: 4.4137. Min Act: -0.1700
Data Index: 4163242 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8200. Min Range: -4.8200
Max Act: 4.4137. Min Act: -0.1700
Data Index: 3815795 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8200. Min Range: -4.8200
Max Act: 4.4450. Min Act: -0.1700
Data Index: 5135011 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8200. Min Range: -4.8200
Max Act: 4.4450. Min Act: -0.1700
Data Index: 1979666 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8200. Min Range: -4.8200
Max Act: 4.4450. Min Act: -0.1700
Data Index: 1936650 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8200. Min Range: -4.8200
Max Act: 4.4450. Min Act: -0.1700
Data Index: 6301440 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8200. Min Range: -4.8200
Max Act: 4.3825. Min Act: -0.1700
Data Index: 4140538 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8200. Min Range: -4.8200
Max Act: 4.4137. Min Act: -0.1700
Data Index: 4284754 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8200. Min Range: -4.8200
Max Act: 4.3825. Min Act: -0.1700
Data Index: 7506951 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8200. Min Range: -4.8200
Max Act: 4.3825. Min Act: -0.1700
Data Index: 6748337 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8200. Min Range: -4.8200
Max Act: 4.3825. Min Act: -0.1700
Data Index: 113107 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8200. Min Range: -4.8200
Max Act: 4.3512. Min Act: -0.1700
Data Index: 2391439 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19