Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1565 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2771. Min Range: -7.2771
Max Act: 7.2771. Min Act: -0.1700
Data Index: 2699105 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.9959. Min Act: -0.1700
Data Index: 511282 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.6209. Min Act: -0.1700
Data Index: 5056167 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.5896. Min Act: -0.1700
Data Index: 731504 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.5896. Min Act: -0.1700
Data Index: 6705391 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.5896. Min Act: -0.1700
Data Index: 7315203 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.4334. Min Act: -0.1700
Data Index: 7208584 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.4334. Min Act: -0.1700
Data Index: 1686577 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.4021. Min Act: -0.1700
Data Index: 1375061 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.3709. Min Act: -0.1700
Data Index: 860402 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.3709. Min Act: -0.1700
Data Index: 584037 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.3709. Min Act: -0.1700
Data Index: 8291944 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.3709. Min Act: -0.1700
Data Index: 7342059 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.3084. Min Act: -0.1700
Data Index: 2560438 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.3084. Min Act: -0.1700
Data Index: 6007004 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.2459. Min Act: -0.1700
Data Index: 3913316 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.2771. Min Act: -0.1700
Data Index: 8826158 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.2771. Min Act: -0.1700
Data Index: 687564 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.2771. Min Act: -0.1700
Data Index: 6874387 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2771. Min Range: -7.2771
Max Act: 6.2459. Min Act: -0.1700
Data Index: 2095323 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19