Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3246 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5463. Min Range: -6.5463
Max Act: 6.5463. Min Act: -0.1700
Data Index: 1327339 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5463. Min Range: -6.5463
Max Act: 6.4838. Min Act: -0.1700
Data Index: 6333821 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5463. Min Range: -6.5463
Max Act: 6.4838. Min Act: -0.1700
Data Index: 5561946 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5463. Min Range: -6.5463
Max Act: 6.4213. Min Act: -0.1700
Data Index: 5502800 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5463. Min Range: -6.5463
Max Act: 6.4213. Min Act: -0.1700
Data Index: 6995313 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5463. Min Range: -6.5463
Max Act: 6.3901. Min Act: -0.1700
Data Index: 8183553 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5463. Min Range: -6.5463
Max Act: 6.3588. Min Act: -0.1700
Data Index: 4008043 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5463. Min Range: -6.5463
Max Act: 6.3276. Min Act: -0.1700
Data Index: 5105340 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5463. Min Range: -6.5463
Max Act: 6.2651. Min Act: -0.1700
Data Index: 390459 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5463. Min Range: -6.5463
Max Act: 6.2963. Min Act: -0.1700
Data Index: 6466403 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5463. Min Range: -6.5463
Max Act: 6.2338. Min Act: -0.1700
Data Index: 3884862 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5463. Min Range: -6.5463
Max Act: 6.2338. Min Act: -0.1700
Data Index: 4502384 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5463. Min Range: -6.5463
Max Act: 6.2338. Min Act: -0.1700
Data Index: 4346046 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5463. Min Range: -6.5463
Max Act: 6.2651. Min Act: -0.1700
Data Index: 1239595 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5463. Min Range: -6.5463
Max Act: 6.2651. Min Act: -0.1700
Data Index: 5024794 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5463. Min Range: -6.5463
Max Act: 6.2026. Min Act: -0.1700
Data Index: 4132455 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5463. Min Range: -6.5463
Max Act: 6.2026. Min Act: -0.1700
Data Index: 7663278 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5463. Min Range: -6.5463
Max Act: 6.2338. Min Act: -0.1699
Data Index: 8146586 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5463. Min Range: -6.5463
Max Act: 6.2338. Min Act: -0.1700
Data Index: 263561 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5463. Min Range: -6.5463
Max Act: 6.2026. Min Act: -0.1700
Data Index: 5084821 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19