Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3333 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7964. Min Range: -6.7964
Max Act: 6.7964. Min Act: -0.1700
Data Index: 3148852 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7964. Min Range: -6.7964
Max Act: 6.5776. Min Act: -0.1700
Data Index: 7775202 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7964. Min Range: -6.7964
Max Act: 6.4839. Min Act: -0.1700
Data Index: 7013964 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7964. Min Range: -6.7964
Max Act: 6.4214. Min Act: -0.1700
Data Index: 8285899 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7964. Min Range: -6.7964
Max Act: 6.4214. Min Act: -0.1700
Data Index: 1869630 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7964. Min Range: -6.7964
Max Act: 6.4214. Min Act: -0.1700
Data Index: 3108991 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7964. Min Range: -6.7964
Max Act: 6.3276. Min Act: -0.1700
Data Index: 3668207 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7964. Min Range: -6.7964
Max Act: 6.3589. Min Act: -0.1700
Data Index: 3331143 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7964. Min Range: -6.7964
Max Act: 6.3589. Min Act: -0.1700
Data Index: 6854600 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7964. Min Range: -6.7964
Max Act: 6.3276. Min Act: -0.1700
Data Index: 2416017 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7964. Min Range: -6.7964
Max Act: 6.2964. Min Act: -0.1700
Data Index: 3541971 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7964. Min Range: -6.7964
Max Act: 6.2964. Min Act: -0.1700
Data Index: 5117356 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7964. Min Range: -6.7964
Max Act: 6.2964. Min Act: -0.1700
Data Index: 7125615 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7964. Min Range: -6.7964
Max Act: 6.2651. Min Act: -0.1700
Data Index: 8321306 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7964. Min Range: -6.7964
Max Act: 6.2651. Min Act: -0.1700
Data Index: 2872941 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7964. Min Range: -6.7964
Max Act: 6.2339. Min Act: -0.1700
Data Index: 2796738 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7964. Min Range: -6.7964
Max Act: 6.2026. Min Act: -0.1700
Data Index: 1728382 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7964. Min Range: -6.7964
Max Act: 6.2026. Min Act: -0.1700
Data Index: 3993984 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7964. Min Range: -6.7964
Max Act: 6.1714. Min Act: -0.1700
Data Index: 350836 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7964. Min Range: -6.7964
Max Act: 6.2026. Min Act: -0.1700
Data Index: 3173057 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #19