Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1025 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2163. Min Range: -4.2163
Max Act: 4.2163. Min Act: -0.1700
Data Index: 5050021 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2163. Min Range: -4.2163
Max Act: 4.0287. Min Act: -0.1700
Data Index: 4520283 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2163. Min Range: -4.2163
Max Act: 3.9975. Min Act: -0.1700
Data Index: 5779343 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2163. Min Range: -4.2163
Max Act: 3.9975. Min Act: -0.1700
Data Index: 2328467 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2163. Min Range: -4.2163
Max Act: 3.9506. Min Act: -0.1700
Data Index: 4737957 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2163. Min Range: -4.2163
Max Act: 3.9349. Min Act: -0.1700
Data Index: 3513756 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2163. Min Range: -4.2163
Max Act: 3.9349. Min Act: -0.1700
Data Index: 253925 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2163. Min Range: -4.2163
Max Act: 3.9037. Min Act: -0.1700
Data Index: 1285357 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2163. Min Range: -4.2163
Max Act: 3.8880. Min Act: -0.1700
Data Index: 6142044 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2163. Min Range: -4.2163
Max Act: 3.8724. Min Act: -0.1700
Data Index: 4445192 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2163. Min Range: -4.2163
Max Act: 3.8880. Min Act: -0.1700
Data Index: 1010859 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2163. Min Range: -4.2163
Max Act: 3.8724. Min Act: -0.1700
Data Index: 5180229 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2163. Min Range: -4.2163
Max Act: 3.8568. Min Act: -0.1700
Data Index: 2244097 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2163. Min Range: -4.2163
Max Act: 3.8255. Min Act: -0.1700
Data Index: 7564457 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2163. Min Range: -4.2163
Max Act: 3.8255. Min Act: -0.1700
Data Index: 316952 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2163. Min Range: -4.2163
Max Act: 3.8255. Min Act: -0.1700
Data Index: 492154 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2163. Min Range: -4.2163
Max Act: 3.8255. Min Act: -0.1700
Data Index: 8058416 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2163. Min Range: -4.2163
Max Act: 3.8099. Min Act: -0.1700
Data Index: 2276774 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2163. Min Range: -4.2163
Max Act: 3.8099. Min Act: -0.1700
Data Index: 3106483 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2163. Min Range: -4.2163
Max Act: 3.7786. Min Act: -0.1700
Data Index: 827194 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19