Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3078 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.3573. Min Act: -0.1700
Data Index: 7587584 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1688. Min Act: -0.1700
Data Index: 5780528 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1688. Min Act: -0.1700
Data Index: 2911275 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1531. Min Act: -0.1700
Data Index: 5744240 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1531. Min Act: -0.1700
Data Index: 8169147 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1373. Min Act: -0.1700
Data Index: 3585866 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1531. Min Act: -0.1700
Data Index: 8085390 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1373. Min Act: -0.1700
Data Index: 6202154 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1216. Min Act: -0.1700
Data Index: 1326687 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1058. Min Act: -0.1700
Data Index: 5621962 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1216. Min Act: -0.1700
Data Index: 3467017 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1058. Min Act: -0.1700
Data Index: 3364400 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1058. Min Act: -0.1700
Data Index: 3135872 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1058. Min Act: -0.1700
Data Index: 7836646 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.1058. Min Act: -0.1700
Data Index: 8027443 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.0901. Min Act: -0.1700
Data Index: 4856983 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.0743. Min Act: -0.1700
Data Index: 608281 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.0743. Min Act: -0.1700
Data Index: 4376325 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.0743. Min Act: -0.1700
Data Index: 1888839 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3573. Min Range: -3.3573
Max Act: 3.0585. Min Act: -0.1700
Data Index: 1852833 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19