Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3433 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2819. Min Range: -5.2819
Max Act: 5.2819. Min Act: -0.1700
Data Index: 3954349 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2819. Min Range: -5.2819
Max Act: 5.0319. Min Act: -0.1700
Data Index: 1706672 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.9069. Min Act: -0.1700
Data Index: 2300518 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.9069. Min Act: -0.1700
Data Index: 6114070 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.8756. Min Act: -0.1700
Data Index: 6859168 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.8444. Min Act: -0.1700
Data Index: 5670613 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.8444. Min Act: -0.1700
Data Index: 1079132 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.8131. Min Act: -0.1700
Data Index: 751116 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.8444. Min Act: -0.1700
Data Index: 2559694 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.7819. Min Act: -0.1700
Data Index: 7680355 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.7506. Min Act: -0.1700
Data Index: 1311354 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.7506. Min Act: -0.1700
Data Index: 8823773 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.7194. Min Act: -0.1700
Data Index: 1522481 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.7194. Min Act: -0.1700
Data Index: 1875435 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.6881. Min Act: -0.1700
Data Index: 2721351 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.6881. Min Act: -0.1700
Data Index: 2180946 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.6881. Min Act: -0.1700
Data Index: 3231360 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.6881. Min Act: -0.1700
Data Index: 1730054 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.6569. Min Act: -0.1700
Data Index: 1803544 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2819. Min Range: -5.2819
Max Act: 4.6569. Min Act: -0.1700
Data Index: 6787730 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19