Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3293 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6161. Min Range: -7.6161
Max Act: 7.6161. Min Act: -0.1700
Data Index: 7326741 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6161. Min Range: -7.6161
Max Act: 7.5849. Min Act: -0.1700
Data Index: 8511571 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6161. Min Range: -7.6161
Max Act: 7.5536. Min Act: -0.1700
Data Index: 6052297 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6161. Min Range: -7.6161
Max Act: 7.4911. Min Act: -0.1700
Data Index: 6401705 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6161. Min Range: -7.6161
Max Act: 7.4286. Min Act: -0.1700
Data Index: 6401252 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6161. Min Range: -7.6161
Max Act: 7.3349. Min Act: -0.1700
Data Index: 6028722 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6161. Min Range: -7.6161
Max Act: 7.3349. Min Act: -0.1700
Data Index: 4485039 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6161. Min Range: -7.6161
Max Act: 7.3661. Min Act: -0.1700
Data Index: 2116925 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6161. Min Range: -7.6161
Max Act: 7.3349. Min Act: -0.1700
Data Index: 7779322 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6161. Min Range: -7.6161
Max Act: 7.3036. Min Act: -0.1700
Data Index: 4960471 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6161. Min Range: -7.6161
Max Act: 7.2724. Min Act: -0.1700
Data Index: 3521363 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6161. Min Range: -7.6161
Max Act: 7.2411. Min Act: -0.1700
Data Index: 1317979 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6161. Min Range: -7.6161
Max Act: 7.2411. Min Act: -0.1700
Data Index: 7942060 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6161. Min Range: -7.6161
Max Act: 7.2099. Min Act: -0.1700
Data Index: 4286476 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6161. Min Range: -7.6161
Max Act: 7.2724. Min Act: -0.1700
Data Index: 5837294 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6161. Min Range: -7.6161
Max Act: 7.2099. Min Act: -0.1700
Data Index: 3391987 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6161. Min Range: -7.6161
Max Act: 7.2411. Min Act: -0.1700
Data Index: 8154154 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6161. Min Range: -7.6161
Max Act: 7.1786. Min Act: -0.1700
Data Index: 1342328 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6161. Min Range: -7.6161
Max Act: 7.1474. Min Act: -0.1700
Data Index: 4463104 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6161. Min Range: -7.6161
Max Act: 7.1161. Min Act: -0.1700
Data Index: 2853071 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19