Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 26 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.9632. Min Act: -0.1700
Data Index: 197460 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.9319. Min Act: -0.1700
Data Index: 5814424 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.9007. Min Act: -0.1700
Data Index: 5814414 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.9007. Min Act: -0.1700
Data Index: 5814422 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.8694. Min Act: -0.1700
Data Index: 5814409 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.8381. Min Act: -0.1700
Data Index: 6182945 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.8069. Min Act: -0.1700
Data Index: 5814426 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.7599. Min Act: -0.1700
Data Index: 5814419 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.7599. Min Act: -0.1700
Data Index: 5814428 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.7443. Min Act: -0.1700
Data Index: 5367548 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.7443. Min Act: -0.1700
Data Index: 5814412 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.7443. Min Act: -0.1700
Data Index: 4657048 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.7287. Min Act: -0.1700
Data Index: 5814432 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.7287. Min Act: -0.1700
Data Index: 5367541 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.7287. Min Act: -0.1700
Data Index: 5814416 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.6817. Min Act: -0.1700
Data Index: 5367537 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.6817. Min Act: -0.1700
Data Index: 5814429 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.6504. Min Act: -0.1700
Data Index: 4970760 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.6504. Min Act: -0.1700
Data Index: 5367531 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9632. Min Range: -3.9632
Max Act: 3.6661. Min Act: -0.1700
Data Index: 2429046 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19