Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1394 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5103. Min Range: -3.5103
Max Act: 3.4946. Min Act: -0.1700
Data Index: 1404753 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5103. Min Range: -3.5103
Max Act: 3.4789. Min Act: -0.1700
Data Index: 2240193 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5103. Min Range: -3.5103
Max Act: 3.5103. Min Act: -0.1700
Data Index: 2315861 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5103. Min Range: -3.5103
Max Act: 3.4789. Min Act: -0.1700
Data Index: 4020413 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5103. Min Range: -3.5103
Max Act: 3.4633. Min Act: -0.1700
Data Index: 4897450 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5103. Min Range: -3.5103
Max Act: 3.4319. Min Act: -0.1700
Data Index: 2524830 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5103. Min Range: -3.5103
Max Act: 3.4319. Min Act: -0.1700
Data Index: 8394653 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5103. Min Range: -3.5103
Max Act: 3.4319. Min Act: -0.1700
Data Index: 1622494 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5103. Min Range: -3.5103
Max Act: 3.4162. Min Act: -0.1700
Data Index: 2049959 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5103. Min Range: -3.5103
Max Act: 3.4476. Min Act: -0.1700
Data Index: 6829060 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5103. Min Range: -3.5103
Max Act: 3.4006. Min Act: -0.1700
Data Index: 7782709 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5103. Min Range: -3.5103
Max Act: 3.4006. Min Act: -0.1700
Data Index: 3923517 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5103. Min Range: -3.5103
Max Act: 3.3692. Min Act: -0.1700
Data Index: 7946173 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5103. Min Range: -3.5103
Max Act: 3.3535. Min Act: -0.1700
Data Index: 5451545 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5103. Min Range: -3.5103
Max Act: 3.3221. Min Act: -0.1700
Data Index: 6718347 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5103. Min Range: -3.5103
Max Act: 3.3064. Min Act: -0.1700
Data Index: 7139608 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5103. Min Range: -3.5103
Max Act: 3.3221. Min Act: -0.1700
Data Index: 1428277 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5103. Min Range: -3.5103
Max Act: 3.3221. Min Act: -0.1700
Data Index: 3924612 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5103. Min Range: -3.5103
Max Act: 3.3064. Min Act: -0.1700
Data Index: 3878198 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5103. Min Range: -3.5103
Max Act: 3.3221. Min Act: -0.1700
Data Index: 1420065 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19