Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2646 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.2943. Min Range: -9.2943
Max Act: 9.2943. Min Act: -0.1700
Data Index: 4780872 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2943. Min Range: -9.2943
Max Act: 9.2943. Min Act: -0.1700
Data Index: 6192444 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2943. Min Range: -9.2943
Max Act: 9.2943. Min Act: -0.1700
Data Index: 5958378 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2943. Min Range: -9.2943
Max Act: 9.2318. Min Act: -0.1700
Data Index: 6111056 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2943. Min Range: -9.2943
Max Act: 9.1068. Min Act: -0.1700
Data Index: 7290130 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2943. Min Range: -9.2943
Max Act: 9.1068. Min Act: -0.1700
Data Index: 4243230 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2943. Min Range: -9.2943
Max Act: 9.1068. Min Act: -0.1700
Data Index: 5994075 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2943. Min Range: -9.2943
Max Act: 9.1068. Min Act: -0.1700
Data Index: 5994076 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2943. Min Range: -9.2943
Max Act: 9.1068. Min Act: -0.1700
Data Index: 828075 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2943. Min Range: -9.2943
Max Act: 9.0443. Min Act: -0.1700
Data Index: 4243229 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2943. Min Range: -9.2943
Max Act: 9.0443. Min Act: -0.1700
Data Index: 828076 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2943. Min Range: -9.2943
Max Act: 9.0443. Min Act: -0.1700
Data Index: 8562327 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2943. Min Range: -9.2943
Max Act: 9.0443. Min Act: -0.1700
Data Index: 7290131 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2943. Min Range: -9.2943
Max Act: 9.0443. Min Act: -0.1700
Data Index: 6192443 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2943. Min Range: -9.2943
Max Act: 9.0443. Min Act: -0.1700
Data Index: 8562328 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2943. Min Range: -9.2943
Max Act: 8.8568. Min Act: -0.1700
Data Index: 5840325 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2943. Min Range: -9.2943
Max Act: 8.3568. Min Act: -0.1700
Data Index: 3925921 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2943. Min Range: -9.2943
Max Act: 8.2943. Min Act: -0.1700
Data Index: 4132606 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2943. Min Range: -9.2943
Max Act: 8.2943. Min Act: -0.1700
Data Index: 5666764 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2943. Min Range: -9.2943
Max Act: 8.2943. Min Act: -0.1700
Data Index: 55008 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19