Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2985 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3139. Min Range: -6.3139
Max Act: 6.2827. Min Act: -0.1700
Data Index: 1020872 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3139. Min Range: -6.3139
Max Act: 6.3139. Min Act: -0.1700
Data Index: 5135890 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3139. Min Range: -6.3139
Max Act: 6.2514. Min Act: -0.1700
Data Index: 3238100 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3139. Min Range: -6.3139
Max Act: 6.2202. Min Act: -0.1700
Data Index: 8259012 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3139. Min Range: -6.3139
Max Act: 6.1889. Min Act: -0.1700
Data Index: 1111132 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3139. Min Range: -6.3139
Max Act: 6.1577. Min Act: -0.1700
Data Index: 5749132 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3139. Min Range: -6.3139
Max Act: 6.1264. Min Act: -0.1700
Data Index: 899659 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3139. Min Range: -6.3139
Max Act: 6.1577. Min Act: -0.1700
Data Index: 1261156 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3139. Min Range: -6.3139
Max Act: 6.0952. Min Act: -0.1700
Data Index: 874056 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3139. Min Range: -6.3139
Max Act: 6.1264. Min Act: -0.1700
Data Index: 8768766 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3139. Min Range: -6.3139
Max Act: 6.0952. Min Act: -0.1700
Data Index: 8248779 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3139. Min Range: -6.3139
Max Act: 6.0952. Min Act: -0.1700
Data Index: 5886056 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3139. Min Range: -6.3139
Max Act: 6.0639. Min Act: -0.1700
Data Index: 5308354 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3139. Min Range: -6.3139
Max Act: 6.0014. Min Act: -0.1700
Data Index: 349467 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.9702. Min Act: -0.1700
Data Index: 7069394 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.9702. Min Act: -0.1700
Data Index: 4828275 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.9389. Min Act: -0.1700
Data Index: 5664699 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.9077. Min Act: -0.1700
Data Index: 5467887 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.9077. Min Act: -0.1700
Data Index: 1923506 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3139. Min Range: -6.3139
Max Act: 5.8764. Min Act: -0.1700
Data Index: 7341649 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19