Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4278 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3177. Min Range: -4.3177
Max Act: 4.3177. Min Act: -0.1700
Data Index: 1019602 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3177. Min Range: -4.3177
Max Act: 4.3177. Min Act: -0.1700
Data Index: 1213181 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3177. Min Range: -4.3177
Max Act: 4.2865. Min Act: -0.1700
Data Index: 1019603 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3177. Min Range: -4.3177
Max Act: 4.2865. Min Act: -0.1700
Data Index: 6929226 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3177. Min Range: -4.3177
Max Act: 4.2240. Min Act: -0.1700
Data Index: 7288644 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3177. Min Range: -4.3177
Max Act: 4.2240. Min Act: -0.1700
Data Index: 3334235 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3177. Min Range: -4.3177
Max Act: 4.2240. Min Act: -0.1700
Data Index: 113443 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3177. Min Range: -4.3177
Max Act: 4.2240. Min Act: -0.1700
Data Index: 5481320 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3177. Min Range: -4.3177
Max Act: 4.2240. Min Act: -0.1700
Data Index: 4077478 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3177. Min Range: -4.3177
Max Act: 4.2240. Min Act: -0.1700
Data Index: 1925497 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3177. Min Range: -4.3177
Max Act: 4.1927. Min Act: -0.1700
Data Index: 5995724 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3177. Min Range: -4.3177
Max Act: 4.1927. Min Act: -0.1700
Data Index: 3492513 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3177. Min Range: -4.3177
Max Act: 4.1615. Min Act: -0.1700
Data Index: 4966224 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3177. Min Range: -4.3177
Max Act: 4.1302. Min Act: -0.1700
Data Index: 8820963 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3177. Min Range: -4.3177
Max Act: 4.1615. Min Act: -0.1700
Data Index: 6913172 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3177. Min Range: -4.3177
Max Act: 4.1927. Min Act: -0.1700
Data Index: 2443701 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3177. Min Range: -4.3177
Max Act: 4.1615. Min Act: -0.1700
Data Index: 5284591 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3177. Min Range: -4.3177
Max Act: 4.1302. Min Act: -0.1700
Data Index: 531178 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3177. Min Range: -4.3177
Max Act: 4.1302. Min Act: -0.1700
Data Index: 2312735 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3177. Min Range: -4.3177
Max Act: 4.0990. Min Act: -0.1700
Data Index: 3602788 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19