Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1209 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5261. Min Range: -3.5261
Max Act: 3.5261. Min Act: -0.1700
Data Index: 7258879 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5261. Min Range: -3.5261
Max Act: 3.3537. Min Act: -0.1700
Data Index: 2996899 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5261. Min Range: -3.5261
Max Act: 3.2909. Min Act: -0.1700
Data Index: 7202670 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5261. Min Range: -3.5261
Max Act: 3.2438. Min Act: -0.1700
Data Index: 8483101 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5261. Min Range: -3.5261
Max Act: 3.2752. Min Act: -0.1700
Data Index: 1904954 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5261. Min Range: -3.5261
Max Act: 3.2438. Min Act: -0.1700
Data Index: 3479742 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5261. Min Range: -3.5261
Max Act: 3.2595. Min Act: -0.1700
Data Index: 330944 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5261. Min Range: -3.5261
Max Act: 3.2281. Min Act: -0.1700
Data Index: 5912106 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5261. Min Range: -3.5261
Max Act: 3.1966. Min Act: -0.1700
Data Index: 8573140 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5261. Min Range: -3.5261
Max Act: 3.1966. Min Act: -0.1700
Data Index: 5965470 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5261. Min Range: -3.5261
Max Act: 3.1966. Min Act: -0.1700
Data Index: 6823476 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5261. Min Range: -3.5261
Max Act: 3.1494. Min Act: -0.1700
Data Index: 396204 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5261. Min Range: -3.5261
Max Act: 3.1494. Min Act: -0.1700
Data Index: 3634211 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5261. Min Range: -3.5261
Max Act: 3.1494. Min Act: -0.1700
Data Index: 6461173 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5261. Min Range: -3.5261
Max Act: 3.1337. Min Act: -0.1700
Data Index: 2907074 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5261. Min Range: -3.5261
Max Act: 3.1179. Min Act: -0.1700
Data Index: 4049435 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5261. Min Range: -3.5261
Max Act: 3.1337. Min Act: -0.1700
Data Index: 8687691 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5261. Min Range: -3.5261
Max Act: 3.1022. Min Act: -0.1700
Data Index: 2143449 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5261. Min Range: -3.5261
Max Act: 3.0864. Min Act: -0.1700
Data Index: 8013110 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5261. Min Range: -3.5261
Max Act: 3.1022. Min Act: -0.1700
Data Index: 7416459 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19